Showing 1–50 of 1,636 results for author: Chen, G

In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data

Authors: Xiongyi Cai, Ri-Zhao Qiu, Geng Chen, Lai Wei, Isabella Liu, Tianshu Huang, Xuxin Cheng, Xiaolong Wang

Abstract: Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simple pre-training, which does not unlock its full potential. This paper first provides a scalable recipe for collecting and using egocentric data by categorizing human data into two categories: in-the-wild and on… ▽ More Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simple pre-training, which does not unlock its full potential. This paper first provides a scalable recipe for collecting and using egocentric data by categorizing human data into two categories: in-the-wild and on-task alongside with systematic analysis on how to use the data. We first curate a dataset, PHSD, which contains over 1,000 hours of diverse in-the-wild egocentric data and over 20 hours of on-task data directly aligned to the target manipulation tasks. This enables learning a large egocentric language-conditioned flow matching policy, Human0. With domain adaptation techniques, Human0 minimizes the gap between humans and humanoids. Empirically, we show Human0 achieves several novel properties from scaling human data, including language following of instructions from only human data, few-shot learning, and improved robustness using on-task data. Project website: https://xiongyicai.github.io/In-N-On/ △ Less

Submitted 19 November, 2025; originally announced November 2025.

Comments: Project webpage: https://xiongyicai.github.io/In-N-On/

A Scenario Approach to the Robustness of Nonconvex-Nonconcave Minimax Problems

Authors: Huan Peng, Guanpu Chen, Karl Henrik Johansson

Abstract: This paper investigates probabilistic robustness of nonconvex-nonconcave minimax problems via the scenario approach. Inspired by recent advances in scenario optimization (Garatti and Campi, 2025), we obtain robustness results for key equilibria with nonconvex-nonconcave payoffs, overcoming the dependence on the non-degeneracy assumption. Specifically, under convex strategy sets for all players, we… ▽ More This paper investigates probabilistic robustness of nonconvex-nonconcave minimax problems via the scenario approach. Inspired by recent advances in scenario optimization (Garatti and Campi, 2025), we obtain robustness results for key equilibria with nonconvex-nonconcave payoffs, overcoming the dependence on the non-degeneracy assumption. Specifically, under convex strategy sets for all players, we first establish a probabilistic robustness guarantee for an epsilon-stationary point by proving the monotonicity of the stationary residual in the number of scenarios. Moreover, under nonconvex strategy sets for all players, we derive a probabilistic robustness guarantee for a global minimax point by invoking the extreme value theorem and Berge's maximum theorem. A numerical experiment on a unit commitment problem corroborates our theoretical findings. △ Less

Submitted 19 November, 2025; originally announced November 2025.

ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions

Authors: Xingwei He, Qianru Zhang, Pengfei Chen, Guanhua Chen, Linlin Yu, Yuan Yuan, Siu-Ming Yiu

Abstract: Instruction-following is a critical capability of Large Language Models (LLMs). While existing works primarily focus on assessing how well LLMs adhere to user instructions, they often overlook scenarios where instructions contain conflicting constraints-a common occurrence in complex prompts. The behavior of LLMs under such conditions remains under-explored. To bridge this gap, we introduce ConIns… ▽ More Instruction-following is a critical capability of Large Language Models (LLMs). While existing works primarily focus on assessing how well LLMs adhere to user instructions, they often overlook scenarios where instructions contain conflicting constraints-a common occurrence in complex prompts. The behavior of LLMs under such conditions remains under-explored. To bridge this gap, we introduce ConInstruct, a benchmark specifically designed to assess LLMs' ability to detect and resolve conflicts within user instructions. Using this dataset, we evaluate LLMs' conflict detection performance and analyze their conflict resolution behavior. Our experiments reveal two key findings: (1) Most proprietary LLMs exhibit strong conflict detection capabilities, whereas among open-source models, only DeepSeek-R1 demonstrates similarly strong performance. DeepSeek-R1 and Claude-4.5-Sonnet achieve the highest average F1-scores at 91.5% and 87.3%, respectively, ranking first and second overall. (2) Despite their strong conflict detection abilities, LLMs rarely explicitly notify users about the conflicts or request clarification when faced with conflicting constraints. These results underscore a critical shortcoming in current LLMs and highlight an important area for future improvement when designing instruction-following LLMs. △ Less

Submitted 19 November, 2025; v1 submitted 18 November, 2025; originally announced November 2025.

Comments: Accepted to AAAI 2026

Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding

Authors: Qingyang Yan, Guangyao Chen, Yixiong Zou

Abstract: Chain-of-Thought (CoT) prompting has recently shown significant promise across various NLP and computer vision tasks by explicitly generating intermediate reasoning steps. However, we find that reinforcement learning (RL)-based fine-tuned CoT reasoning can paradoxically degrade performance in Visual Grounding tasks, particularly as CoT outputs become lengthy or complex. Additionally, our analysis… ▽ More Chain-of-Thought (CoT) prompting has recently shown significant promise across various NLP and computer vision tasks by explicitly generating intermediate reasoning steps. However, we find that reinforcement learning (RL)-based fine-tuned CoT reasoning can paradoxically degrade performance in Visual Grounding tasks, particularly as CoT outputs become lengthy or complex. Additionally, our analysis reveals that increased dataset size does not always enhance performance due to varying data complexities. Motivated by these findings, we propose Curriculum-based Relative Policy Optimization (CuRPO), a novel training strategy that leverages CoT length and generalized Intersection over Union (gIoU) rewards as complexity indicators to progressively structure training data from simpler to more challenging examples. Extensive experiments on RefCOCO, RefCOCO+, RefCOCOg, and LISA datasets demonstrate the effectiveness of our approach. CuRPO consistently outperforms existing methods, including Visual-RFT, with notable improvements of up to +12.52 mAP on RefCOCO. Moreover, CuRPO exhibits exceptional efficiency and robustness, delivering strong localization performance even in few-shot learning scenarios, particularly benefiting tasks characterized by ambiguous and intricate textual descriptions.The code is released on https://github.com/qyoung-yan/CuRPO. △ Less

Submitted 17 November, 2025; originally announced November 2025.

Comments: AAAI 2026 (Oral)

SkyReels-Text: Fine-grained Font-Controllable Text Editing for Poster Design

Authors: Yunjie Yu, Jingchen Wu, Junchen Zhu, Chunze Lin, Guibin Chen

Abstract: Artistic design such as poster design often demands rapid yet precise modification of textual content while preserving visual harmony and typographic intent, especially across diverse font styles. Although modern image editing models have grown increasingly powerful, they still fall short in fine-grained, font-aware text manipulation, limiting their utility in professional design workflows such as… ▽ More Artistic design such as poster design often demands rapid yet precise modification of textual content while preserving visual harmony and typographic intent, especially across diverse font styles. Although modern image editing models have grown increasingly powerful, they still fall short in fine-grained, font-aware text manipulation, limiting their utility in professional design workflows such as poster editing. To address this issue, we present SkyReels-Text, a novel font-controllable framework for precise poster text editing. Our method enables simultaneous editing of multiple text regions, each rendered in distinct typographic styles, while preserving the visual appearance of non-edited regions. Notably, our model requires neither font labels nor fine-tuning during inference: users can simply provide cropped glyph patches corresponding to their desired typography, even if the font is not included in any standard library. Extensive experiments on multiple datasets, including handwrittent text benchmarks, SkyReels-Text achieves state-of-the-art performance in both text fidelity and visual realism, offering unprecedented control over font families, and stylistic nuances. This work bridges the gap between general-purpose image editing and professional-grade typographic design. △ Less

Submitted 17 November, 2025; originally announced November 2025.

CloseUpShot: Close-up Novel View Synthesis from Sparse-views via Point-conditioned Diffusion Model

Authors: Yuqi Zhang, Guanying Chen, Jiaxing Chen, Chuanyu Fu, Chuan Huang, Shuguang Cui

Abstract: Reconstructing 3D scenes and synthesizing novel views from sparse input views is a highly challenging task. Recent advances in video diffusion models have demonstrated strong temporal reasoning capabilities, making them a promising tool for enhancing reconstruction quality under sparse-view settings. However, existing approaches are primarily designed for modest viewpoint variations, which struggl… ▽ More Reconstructing 3D scenes and synthesizing novel views from sparse input views is a highly challenging task. Recent advances in video diffusion models have demonstrated strong temporal reasoning capabilities, making them a promising tool for enhancing reconstruction quality under sparse-view settings. However, existing approaches are primarily designed for modest viewpoint variations, which struggle in capturing fine-grained details in close-up scenarios since input information is severely limited. In this paper, we present a diffusion-based framework, called CloseUpShot, for close-up novel view synthesis from sparse inputs via point-conditioned video diffusion. Specifically, we observe that pixel-warping conditioning suffers from severe sparsity and background leakage in close-up settings. To address this, we propose hierarchical warping and occlusion-aware noise suppression, enhancing the quality and completeness of the conditioning images for the video diffusion model. Furthermore, we introduce global structure guidance, which leverages a dense fused point cloud to provide consistent geometric context to the diffusion process, to compensate for the lack of globally consistent 3D constraints in sparse conditioning inputs. Extensive experiments on multiple datasets demonstrate that our method outperforms existing approaches, especially in close-up novel view synthesis, clearly validating the effectiveness of our design. △ Less

Submitted 17 November, 2025; originally announced November 2025.

Comments: Project Link: https://zyqz97.github.io/CloseUpShot/

DiffuDepGrasp: Diffusion-based Depth Noise Modeling Empowers Sim2Real Robotic Grasping

Authors: Yingting Zhou, Wenbo Cui, Weiheng Liu, Guixing Chen, Haoran Li, Dongbin Zhao

Abstract: Transferring the depth-based end-to-end policy trained in simulation to physical robots can yield an efficient and robust grasping policy, yet sensor artifacts in real depth maps like voids and noise establish a significant sim2real gap that critically impedes policy transfer. Training-time strategies like procedural noise injection or learned mappings suffer from data inefficiency due to unrealis… ▽ More Transferring the depth-based end-to-end policy trained in simulation to physical robots can yield an efficient and robust grasping policy, yet sensor artifacts in real depth maps like voids and noise establish a significant sim2real gap that critically impedes policy transfer. Training-time strategies like procedural noise injection or learned mappings suffer from data inefficiency due to unrealistic noise simulation, which is often ineffective for grasping tasks that require fine manipulation or dependency on paired datasets heavily. Furthermore, leveraging foundation models to reduce the sim2real gap via intermediate representations fails to mitigate the domain shift fully and adds computational overhead during deployment. This work confronts dual challenges of data inefficiency and deployment complexity. We propose DiffuDepGrasp, a deploy-efficient sim2real framework enabling zero-shot transfer through simulation-exclusive policy training. Its core innovation, the Diffusion Depth Generator, synthesizes geometrically pristine simulation depth with learned sensor-realistic noise via two synergistic modules. The first Diffusion Depth Module leverages temporal geometric priors to enable sample-efficient training of a conditional diffusion model that captures complex sensor noise distributions, while the second Noise Grafting Module preserves metric accuracy during perceptual artifact injection. With only raw depth inputs during deployment, DiffuDepGrasp eliminates computational overhead and achieves a 95.7% average success rate on 12-object grasping with zero-shot transfer and strong generalization to unseen objects.Project website: https://diffudepgrasp.github.io/. △ Less

Submitted 16 November, 2025; originally announced November 2025.

MixAR: Mixture Autoregressive Image Generation

Authors: Jinyuan Hu, Jiayou Zhang, Shaobo Cui, Kun Zhang, Guangyi Chen

Abstract: Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the quantization process and the limited codebook size inevitably discard fine-grained information, placing bottlenecks on fidelity. Motivated by this limitation, recent studies have explored autoregressive modeling in continu… ▽ More Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the quantization process and the limited codebook size inevitably discard fine-grained information, placing bottlenecks on fidelity. Motivated by this limitation, recent studies have explored autoregressive modeling in continuous latent spaces, which offers higher generation quality. Yet, unlike discrete tokens constrained by a fixed codebook, continuous representations lie in a vast and unstructured space, posing significant challenges for efficient autoregressive modeling. To address these challenges, we introduce MixAR, a novel framework that leverages mixture training paradigms to inject discrete tokens as prior guidance for continuous AR modeling. MixAR is a factorized formulation that leverages discrete tokens as prior guidance for continuous autoregressive prediction. We investigate several discrete-continuous mixture strategies, including self-attention (DC-SA), cross-attention (DC-CA), and a simple approach (DC-Mix) that replaces homogeneous mask tokens with informative discrete counterparts. Moreover, to bridge the gap between ground-truth training tokens and inference tokens produced by the pre-trained AR model, we propose Training-Inference Mixture (TI-Mix) to achieve consistent training and generation distributions. In our experiments, we demonstrate a favorable balance of the DC-Mix strategy between computational efficiency and generation fidelity, and consistent improvement of TI-Mix. △ Less

Submitted 15 November, 2025; originally announced November 2025.

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

Authors: MiroMind Team, Song Bai, Lidong Bing, Carson Chen, Guanzheng Chen, Yuntao Chen, Zhe Chen, Ziyi Chen, Jifeng Dai, Xuan Dong, Wenhan Dou, Yue Deng, Yunjie Fu, Junqi Ge, Chenxia Han, Tammy Huang, Zhenhang Huang, Jerry Jiao, Shilei Jiang, Tianyu Jiao, Xiaoqi Jian, Lei Lei, Ruilin Li, Ryan Luo, Tiantong Li , et al. (30 additional authors not shown)

Abstract: We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or context length, MiroThinker explores interaction scaling at the model level, systematically training the model to handle deeper and more frequent agent-environment interactions as a third dimension of p… ▽ More We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or context length, MiroThinker explores interaction scaling at the model level, systematically training the model to handle deeper and more frequent agent-environment interactions as a third dimension of performance improvement. Unlike LLM test-time scaling, which operates in isolation and risks degradation with longer reasoning chains, interactive scaling leverages environment feedback and external information acquisition to correct errors and refine trajectories. Through reinforcement learning, the model achieves efficient interaction scaling: with a 256K context window, it can perform up to 600 tool calls per task, enabling sustained multi-turn reasoning and complex real-world research workflows. Across four representative benchmarks-GAIA, HLE, BrowseComp, and BrowseComp-ZH-the 72B variant achieves up to 81.9%, 37.7%, 47.1%, and 55.6% accuracy respectively, surpassing previous open-source agents and approaching commercial counterparts such as GPT-5-high. Our analysis reveals that MiroThinker benefits from interactive scaling consistently: research performance improves predictably as the model engages in deeper and more frequent agent-environment interactions, demonstrating that interaction depth exhibits scaling behaviors analogous to model size and context length. These findings establish interaction scaling as a third critical dimension for building next-generation open research agents, complementing model capacity and context windows. △ Less

Submitted 18 November, 2025; v1 submitted 14 November, 2025; originally announced November 2025.

Comments: Technical Report

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput

Authors: Jingwei Song, Wanyi Chen, Xinyuan Song, Max, Chris Tong, Gufeng Chen, Tianyi Zhao, Eric Yang, Bill Shi, Lynn Ai

Abstract: Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in decentralized settings, where network latency often dominates compute, remains under-characterized. We present Decentralized Speculative Decoding (DSD), a plug-and-play… ▽ More Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in decentralized settings, where network latency often dominates compute, remains under-characterized. We present Decentralized Speculative Decoding (DSD), a plug-and-play framework for decentralized inference that turns communication delay into useful computation by verifying multiple candidate tokens in parallel across distributed nodes. We further introduce an adaptive speculative verification strategy that adjusts acceptance thresholds by token-level semantic importance, delivering an additional 15% to 20% end-to-end speedup without retraining. In theory, DSD reduces cross-node communication cost by approximately (N-1)t1(k-1)/k, where t1 is per-link latency and k is the average number of tokens accepted per round. In practice, DSD achieves up to 2.56x speedup on HumanEval and 2.59x on GSM8K, surpassing the Eagle3 baseline while preserving accuracy. These results show that adapting speculative decoding for decentralized execution provides a system-level optimization that converts network stalls into throughput, enabling faster distributed LLM inference with no model retraining or architectural changes. △ Less

Submitted 13 November, 2025; originally announced November 2025.

Comments: 6 pages, 2 figures, 2 tables. Uses ICML 2025 style

AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning

Authors: Jirong Zha, Yuxuan Fan, Tianyu Zhang, Geng Chen, Yingfeng Chen, Chen Gao, Xinlei Chen

Abstract: Multimodal Large Language Models (MLLMs) have shown promise in single-agent vision tasks, yet benchmarks for evaluating multi-agent collaborative perception remain scarce. This gap is critical, as multi-drone systems provide enhanced coverage, robustness, and collaboration compared to single-sensor setups. Existing multi-image benchmarks mainly target basic perception tasks using high-quality sing… ▽ More Multimodal Large Language Models (MLLMs) have shown promise in single-agent vision tasks, yet benchmarks for evaluating multi-agent collaborative perception remain scarce. This gap is critical, as multi-drone systems provide enhanced coverage, robustness, and collaboration compared to single-sensor setups. Existing multi-image benchmarks mainly target basic perception tasks using high-quality single-agent images, thus failing to evaluate MLLMs in more complex, egocentric collaborative scenarios, especially under real-world degraded perception conditions.To address these challenges, we introduce AirCopBench, the first comprehensive benchmark designed to evaluate MLLMs in embodied aerial collaborative perception under challenging perceptual conditions. AirCopBench includes 14.6k+ questions derived from both simulator and real-world data, spanning four key task dimensions: Scene Understanding, Object Understanding, Perception Assessment, and Collaborative Decision, across 14 task types. We construct the benchmark using data from challenging degraded-perception scenarios with annotated collaborative events, generating large-scale questions through model-, rule-, and human-based methods under rigorous quality control. Evaluations on 40 MLLMs show significant performance gaps in collaborative perception tasks, with the best model trailing humans by 24.38% on average and exhibiting inconsistent results across tasks. Fine-tuning experiments further confirm the feasibility of sim-to-real transfer in aerial collaborative perception and reasoning. △ Less

Submitted 14 November, 2025; originally announced November 2025.

Synthetic Voices, Real Threats: Evaluating Large Text-to-Speech Models in Generating Harmful Audio

Authors: Guangke Chen, Yuhui Wang, Shouling Ji, Xiapu Luo, Ting Wang

Abstract: Modern text-to-speech (TTS) systems, particularly those built on Large Audio-Language Models (LALMs), generate high-fidelity speech that faithfully reproduces input text and mimics specified speaker identities. While prior misuse studies have focused on speaker impersonation, this work explores a distinct content-centric threat: exploiting TTS systems to produce speech containing harmful content.… ▽ More Modern text-to-speech (TTS) systems, particularly those built on Large Audio-Language Models (LALMs), generate high-fidelity speech that faithfully reproduces input text and mimics specified speaker identities. While prior misuse studies have focused on speaker impersonation, this work explores a distinct content-centric threat: exploiting TTS systems to produce speech containing harmful content. Realizing such threats poses two core challenges: (1) LALM safety alignment frequently rejects harmful prompts, yet existing jailbreak attacks are ill-suited for TTS because these systems are designed to faithfully vocalize any input text, and (2) real-world deployment pipelines often employ input/output filters that block harmful text and audio. We present HARMGEN, a suite of five attacks organized into two families that address these challenges. The first family employs semantic obfuscation techniques (Concat, Shuffle) that conceal harmful content within text. The second leverages audio-modality exploits (Read, Spell, Phoneme) that inject harmful content through auxiliary audio channels while maintaining benign textual prompts. Through evaluation across five commercial LALMs-based TTS systems and three datasets spanning two languages, we demonstrate that our attacks substantially reduce refusal rates and increase the toxicity of generated speech. We further assess both reactive countermeasures deployed by audio-streaming platforms and proactive defenses implemented by TTS providers. Our analysis reveals critical vulnerabilities: deepfake detectors underperform on high-fidelity audio; reactive moderation can be circumvented by adversarial perturbations; while proactive moderation detects 57-93% of attacks. Our work highlights a previously underexplored content-centric misuse vector for TTS and underscore the need for robust cross-modal safeguards throughout training and deployment. △ Less

Submitted 13 November, 2025; originally announced November 2025.

Boosting In-Silicon Directed Evolution with Fine-Tuned Protein Language Model and Tree Search

Authors: Yaodong Yang, Yang Wang, Jinpeng Li, Pei Guo, Da Han, Guangyong Chen, Pheng-Ann Heng

Abstract: Protein evolution through amino acid sequence mutations is a cornerstone of life sciences. While current in-silicon directed evolution algorithms largely focus on designing heuristic search strategies, they overlook how to integrate the transformative protein language models, which encode rich evolutionary patterns, with reinforcement learning to learn to directly evolve proteins. To bridge this g… ▽ More Protein evolution through amino acid sequence mutations is a cornerstone of life sciences. While current in-silicon directed evolution algorithms largely focus on designing heuristic search strategies, they overlook how to integrate the transformative protein language models, which encode rich evolutionary patterns, with reinforcement learning to learn to directly evolve proteins. To bridge this gap, we propose AlphaDE, a novel framework to optimize protein sequences by harnessing the innovative paradigms of large language models such as fine-tuning and test-time inference. First, AlphaDE fine-tunes pretrained protein language models using masked language modeling on homologous protein sequences to activate the evolutionary plausibility for the interested protein class. Second, AlphaDE introduces test-time inference based on Monte Carlo tree search, which effectively evolves proteins with evolutionary guidance from the fine-tuned protein language model. Extensive benchmark experiments show that AlphaDE remarkably outperforms previous state-of-the-art methods even with few-shot fine-tuning. A further case study demonstrates that AlphaDE supports condensing the protein sequence space of avGFP through computational evolution. △ Less

Submitted 19 November, 2025; v1 submitted 12 November, 2025; originally announced November 2025.

Comments: working in progress, 26 pages, 6 figures, 16 tables, updated with more baselines and related works

DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior

Authors: Ruiyang Ma, Yunhao Zhou, Yipeng Wang, Yi Liu, Zhengyuan Shi, Ziyang Zheng, Kexin Chen, Zhiqiang He, Lingwei Yan, Gang Chen, Qiang Xu, Guojie Luo

Abstract: There is a growing body of work on using Graph Neural Networks (GNNs) to learn representations of circuits, focusing primarily on their static characteristics. However, these models fail to capture circuit runtime behavior, which is crucial for tasks like circuit verification and optimization. To address this limitation, we introduce DR-GNN (DynamicRTL-GNN), a novel approach that learns RTL circui… ▽ More There is a growing body of work on using Graph Neural Networks (GNNs) to learn representations of circuits, focusing primarily on their static characteristics. However, these models fail to capture circuit runtime behavior, which is crucial for tasks like circuit verification and optimization. To address this limitation, we introduce DR-GNN (DynamicRTL-GNN), a novel approach that learns RTL circuit representations by incorporating both static structures and multi-cycle execution behaviors. DR-GNN leverages an operator-level Control Data Flow Graph (CDFG) to represent Register Transfer Level (RTL) circuits, enabling the model to capture dynamic dependencies and runtime execution. To train and evaluate DR-GNN, we build the first comprehensive dynamic circuit dataset, comprising over 6,300 Verilog designs and 63,000 simulation traces. Our results demonstrate that DR-GNN outperforms existing models in branch hit prediction and toggle rate prediction. Furthermore, its learned representations transfer effectively to related dynamic circuit tasks, achieving strong performance in power estimation and assertion prediction. △ Less

Submitted 12 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI'2026

Boosting Adversarial Transferability via Ensemble Non-Attention

Authors: Yipeng Zou, Qin Liu, Jie Wu, Yu Peng, Guo Chen, Hui Zhou, Guanghui Ye

Abstract: Ensemble attacks integrate the outputs of surrogate models with diverse architectures, which can be combined with various gradient-based attacks to improve adversarial transferability. However, previous work shows unsatisfactory attack performance when transferring across heterogeneous model architectures. The main reason is that the gradient update directions of heterogeneous surrogate models dif… ▽ More Ensemble attacks integrate the outputs of surrogate models with diverse architectures, which can be combined with various gradient-based attacks to improve adversarial transferability. However, previous work shows unsatisfactory attack performance when transferring across heterogeneous model architectures. The main reason is that the gradient update directions of heterogeneous surrogate models differ widely, making it hard to reduce the gradient variance of ensemble models while making the best of individual model. To tackle this challenge, we design a novel ensemble attack, NAMEA, which for the first time integrates the gradients from the non-attention areas of ensemble models into the iterative gradient optimization process. Our design is inspired by the observation that the attention areas of heterogeneous models vary sharply, thus the non-attention areas of ViTs are likely to be the focus of CNNs and vice versa. Therefore, we merge the gradients respectively from the attention and non-attention areas of ensemble models so as to fuse the transfer information of CNNs and ViTs. Specifically, we pioneer a new way of decoupling the gradients of non-attention areas from those of attention areas, while merging gradients by meta-learning. Empirical evaluations on ImageNet dataset indicate that NAMEA outperforms AdaEA and SMER, the state-of-the-art ensemble attacks by an average of 15.0% and 9.6%, respectively. This work is the first attempt to explore the power of ensemble non-attention in boosting cross-architecture transferability, providing new insights into launching ensemble attacks. △ Less

Submitted 13 November, 2025; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: 16 pages, 11 figures, accepted by AAAI 2026

IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction

Authors: Guoxin Chen, Zile Qiao, Xuanzhong Chen, Donglei Yu, Haotian Xu, Wayne Xin Zhao, Ruihua Song, Wenbiao Yin, Huifeng Yin, Liwen Zhang, Kuan Li, Minpeng Liao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

Abstract: Recent advances in deep-research agents have shown promise for autonomous knowledge construction through dynamic reasoning over external sources. However, existing approaches rely on a mono-contextual paradigm that accumulates all information in a single, expanding context window, leading to context suffocation and noise contamination that limit their effectiveness on long-horizon tasks. We introd… ▽ More Recent advances in deep-research agents have shown promise for autonomous knowledge construction through dynamic reasoning over external sources. However, existing approaches rely on a mono-contextual paradigm that accumulates all information in a single, expanding context window, leading to context suffocation and noise contamination that limit their effectiveness on long-horizon tasks. We introduce IterResearch, a novel iterative deep-research paradigm that reformulates long-horizon research as a Markov Decision Process with strategic workspace reconstruction. By maintaining an evolving report as memory and periodically synthesizing insights, our approach preserves consistent reasoning capacity across arbitrary exploration depths. We further develop Efficiency-Aware Policy Optimization (EAPO), a reinforcement learning framework that incentivizes efficient exploration through geometric reward discounting and enables stable distributed training via adaptive downsampling. Extensive experiments demonstrate that IterResearch achieves substantial improvements over existing open-source agents with average +14.5pp across six benchmarks and narrows the gap with frontier proprietary systems. Remarkably, our paradigm exhibits unprecedented interaction scaling, extending to 2048 interactions with dramatic performance gains (from 3.5\% to 42.5\%), and serves as an effective prompting strategy, improving frontier models by up to 19.2pp over ReAct on long-horizon tasks. These findings position IterResearch as a versatile solution for long-horizon reasoning, effective both as a trained agent and as a prompting paradigm for frontier models. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Comments: https://github.com/Alibaba-NLP/DeepResearch

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation

Authors: Speed Zhu, Jianwei Cai, Guang Chen, Lulu Wu, Saiyong Yang, Wiggin Zhou

Abstract: Recent reasoning-first models (e.g., OpenAI o1, DeepSeek R1) have spurred a resurgence of interest in RLVR. Nevertheless, advances are dominated by mathematics (e.g., AIME), with competitive-programming code generation underexplored and data curation receiving less attention than RL algorithm design. We investigate how to construct RLVR datasets (i.e., RL prompts) and present practical training te… ▽ More Recent reasoning-first models (e.g., OpenAI o1, DeepSeek R1) have spurred a resurgence of interest in RLVR. Nevertheless, advances are dominated by mathematics (e.g., AIME), with competitive-programming code generation underexplored and data curation receiving less attention than RL algorithm design. We investigate how to construct RLVR datasets (i.e., RL prompts) and present practical training techniques that yield strong performance on competitive-programming code generation. Our pipeline begins with supervised fine-tuning (SFT) distilled from strong open-source models, augmented with general-purpose and reasoning-intensive data. RL then follows a two-stage process with executable, testcase-driven rewards: first, training on a large, uniformly distributed set of competitive-programming problems using Group Relative Policy Optimization (GRPO) with 8 rollouts per prompt and a relatively short response-generation window (e.g., 32k during SFT and 24k in this stage) to expand entropy and mitigate repetition and truncation; second, we perform \textbf{Pre-GRPO}: updating on a small, high-quality set of challenging problems with a large rollout budget (64 rollouts per prompt) under a hard-focus curriculum that continuously retains the most difficult instances throughout training. We implement our method on Qwen2.5-32B and evaluate on LeetCode and Codeforces weekly contests to avoid data leakage. The resulting model achieves state-of-the-art performance among models of similar scale and is comparable to leading systems such as DeepSeek v3.1 and Doubao-1.5-Thinking. We also examine scaling trends and observe strong RL scaling on an internal large-scale MoE model. Our study distills concise best practices for data curation, entropy expansion, and curriculum design in RLVR for competitive-programming code generation. △ Less

Submitted 9 November, 2025; originally announced November 2025.

Comments: 15 pages, 8 figures

Report from Workshop on Dialogue alongside Artificial Intelligence

Authors: Thomas J McKenna, Ingvill Rasmussen, Sten Ludvigsen, Avivit Arvatz, Christa Asterhan, Gaowei Chen, Julie Cohen, Michele Flammia, Dongkeun Han, Emma Hayward, Heather Hill, Yifat Kolikant, Helen Lehndorf, Kexin Li, Lindsay Clare Matsumura, Henrik Tjønn, Pengjin Wang, Rupert Wegerif

Abstract: Educational dialogue -- the collaborative exchange of ideas through talk -- is widely recognized as a catalyst for deeper learning and critical thinking in and across contexts. At the same time, artificial intelligence (AI) has rapidly emerged as a powerful force in education, with the potential to address major challenges, personalize learning, and innovate teaching practices. However, these adva… ▽ More Educational dialogue -- the collaborative exchange of ideas through talk -- is widely recognized as a catalyst for deeper learning and critical thinking in and across contexts. At the same time, artificial intelligence (AI) has rapidly emerged as a powerful force in education, with the potential to address major challenges, personalize learning, and innovate teaching practices. However, these advances come with significant risks: rapid AI development can undermine human agency, exacerbate inequities, and outpace our capacity to guide its use with sound policy. Human learning presupposes cognitive efforts and social interaction (dialogues). In response to this evolving landscape, an international workshop titled "Educational Dialogue: Moving Thinking Forward" convened 19 leading researchers from 11 countries in Cambridge (September 1-3, 2025) to examine the intersection of AI and educational dialogue. This AI-focused strand of the workshop centered on three critical questions: (1) When is AI truly useful in education, and when might it merely replace human effort at the expense of learning? (2) Under what conditions can AI use lead to better dialogic teaching and learning? (3) Does the AI-human partnership risk outpacing and displacing human educational work, and what are the implications? These questions framed two days of presentations and structured dialogue among participants. △ Less

Submitted 10 November, 2025; v1 submitted 6 November, 2025; originally announced November 2025.

Comments: Report from the Workshop on Dialogue alongside Artificial Intelligence (2025)

NVIDIA Nemotron Nano V2 VL

Authors: NVIDIA, :, Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki, Matthieu Le, Tyler Poon, Danial Mohseni Taheri, Ilia Karmanov, Guilin Liu, Jarno Seppanen, Guo Chen, Karan Sapra, Zhiding Yu, Adi Renduchintala, Charles Wang, Peter Jin, Arushi Goel, Mike Ranzinger, Lukas Voegtle, Philipp Fischer, Timo Roman, Wei Ping, Boxin Wang, Zhuolin Yang , et al. (99 additional authors not shown)

Abstract: We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our previous model, Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major enhancements in model architecture, datasets, and… ▽ More We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our previous model, Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major enhancements in model architecture, datasets, and training recipes. Nemotron Nano V2 VL builds on Nemotron Nano V2, a hybrid Mamba-Transformer LLM, and innovative token reduction techniques to achieve higher inference throughput in long document and video scenarios. We are releasing model checkpoints in BF16, FP8, and FP4 formats and sharing large parts of our datasets, recipes and training code. △ Less

Submitted 6 November, 2025; v1 submitted 5 November, 2025; originally announced November 2025.

AI-Enhanced Wi-Fi Sensing Through Single Transceiver Pair

Authors: Yuxuan Liu, Chiya Zhang, Yifeng Yuan, Chunlong He, Weizheng Zhang, Gaojie Chen

Abstract: The advancement of next-generation Wi-Fi technology heavily relies on sensing capabilities, which play a pivotal role in enabling sophisticated applications. In response to the growing demand for large-scale deployments, contemporary Wi-Fi sensing systems strive to achieve high-precision perception while maintaining minimal bandwidth consumption and antenna count requirements. Remarkably, various… ▽ More The advancement of next-generation Wi-Fi technology heavily relies on sensing capabilities, which play a pivotal role in enabling sophisticated applications. In response to the growing demand for large-scale deployments, contemporary Wi-Fi sensing systems strive to achieve high-precision perception while maintaining minimal bandwidth consumption and antenna count requirements. Remarkably, various AI-driven perception technologies have demonstrated the ability to surpass the traditional resolution limitations imposed by radar theory. However, the theoretical underpinnings of this phenomenon have not been thoroughly investigated in existing research. In this study, we found that under hardware-constrained conditions, the performance gains brought by AI to Wi-Fi sensing systems primarily originate from two aspects: prior information and temporal correlation. Prior information enables the AI to generate plausible details based on vague input, while temporal correlation helps reduce the upper bound of sensing error. We developed an AI-based Wi-Fi sensing system using a single transceiver pair and designed experiments focusing on human pose estimation and indoor localization to validate the theoretical claims. The results confirm the performance gains contributed by temporal correlation and prior information. △ Less

Submitted 21 October, 2025; originally announced November 2025.

Comments: 12 pages, 11 figures

HGraphScale: Hierarchical Graph Learning for Autoscaling Microservice Applications in Container-based Cloud Computing

Authors: Zhengxin Fang, Hui Ma, Gang Chen, Rajkumar Buyya

Abstract: Microservice architecture has become a dominant paradigm in application development due to its advantages of being lightweight, flexible, and resilient. Deploying microservice applications in the container-based cloud enables fine-grained elastic resource allocation. Autoscaling is an effective approach to dynamically adjust the resource provisioned to containers. However, the intricate microservi… ▽ More Microservice architecture has become a dominant paradigm in application development due to its advantages of being lightweight, flexible, and resilient. Deploying microservice applications in the container-based cloud enables fine-grained elastic resource allocation. Autoscaling is an effective approach to dynamically adjust the resource provisioned to containers. However, the intricate microservice dependencies and the deployment scheme of the container-based cloud bring extra challenges of resource scaling. This article proposes a novel autoscaling approach named HGraphScale. In particular, HGraphScale captures microservice dependencies and the deployment scheme by a newly designed hierarchical graph neural network, and makes effective scaling actions for rapidly changing user requests workloads. Extensive experiments based on real-world traces of user requests are conducted to evaluate the effectiveness of HGraphScale. The experiment results show that the HGraphScale outperforms existing state-of-the-art autoscaling approaches by reducing at most 80.16\% of the average response time under a certain VM rental budget of application providers. △ Less

Submitted 23 October, 2025; originally announced November 2025.

SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia

Authors: Chaoqun Liu, Mahani Aljunied, Guizhen Chen, Hou Pong Chan, Weiwen Xu, Yu Rong, Wenxuan Zhang

Abstract: We introduce SeaLLMs-Audio, the first large audio-language model (LALM) tailored for multiple Southeast Asian (SEA) languages-Indonesian (id), Thai (th), and Vietnamese (vi)-alongside English (en) and Chinese (zh). Trained on a large-scale audio corpus, SeaLLMs-Audio exhibits strong performance across diverse audio-centric tasks, spanning fine-grained audio understanding and voice-based interactio… ▽ More We introduce SeaLLMs-Audio, the first large audio-language model (LALM) tailored for multiple Southeast Asian (SEA) languages-Indonesian (id), Thai (th), and Vietnamese (vi)-alongside English (en) and Chinese (zh). Trained on a large-scale audio corpus, SeaLLMs-Audio exhibits strong performance across diverse audio-centric tasks, spanning fine-grained audio understanding and voice-based interaction. Its key features include: 1) Multilingual: the model primarily supports 5 languages, namely Indonesian, Thai, Vietnamese, English, and Chinese; 2) Multimodal: the model accepts flexible input modalities, including audio only, text only, as well as audio with text; 3) Multi-task: the model supports a wide range of tasks, including audio analysis tasks such as Audio Captioning, Automatic Speech Recognition, Speech-to-Text Translation, Speech Emotion Recognition, Speech Question Answering, and Speech Summarization. It also enables voice-based dialogue, including answering factual, mathematical, and general knowledge queries. As a significant step towards advancing audio LLMs in Southeast Asia, we expect SeaLLMs-Audio to benefit both the regional research community and industry. To automate LALM evaluation for Southeast Asia, we introduce SeaBench-Audio, a benchmark spanning multiple tasks. Experiments show that SeaLLMs-Audio achieves competitive performance compared with other LALMs on SEA languages. △ Less

Submitted 3 November, 2025; originally announced November 2025.

Comments: 10 pages

Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving

Authors: Chengying Huan, Ziheng Meng, Yongchao Liu, Zhengyi Yang, Yun Zhu, Yue Yun, Shipeng Li, Rong Gu, Xiabao Wu, Haitao Zhang, Chuntao Hong, Shaonan Ma, Guihai Chen, Chen Tian

Abstract: Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low throughput due to single-agent monolithic prompts, repeated context re-encoding, and inefficient serving execution. We present GLM, the first multi-agent Graph-CoT sys… ▽ More Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low throughput due to single-agent monolithic prompts, repeated context re-encoding, and inefficient serving execution. We present GLM, the first multi-agent Graph-CoT system co-designed with an optimized LLM serving architecture. GLM decomposes reasoning into specialized agents for classification, reasoning, action generation, and graph retrieval, enabling branching and selective context sharing to reduce prompt length and reasoning iterations while preserving reasoning quality, thereby improving accuracy and reducing overall token consumption. To scale inference, we introduce a Graph-CoT-aware LLM inference mechanism with graph-specific KV-cache management, priority-based eviction, and pipelined execution to improve serving efficiency. Experiments demonstrate that GLM improves answer accuracy by up to 38%, reduces token cost by up to 95.7%, lowers inference latency by 90.3%, and achieves up to 15.1x higher throughput compared to state-of-the-art Graph-CoT baselines, enabling efficient adoption for complex real-world reasoning at scale. △ Less

Submitted 3 November, 2025; originally announced November 2025.

A Saddle Point Remedy: Power of Variable Elimination in Non-convex Optimization

Authors: Min Gan, Guang-Yong Chen, Yang Yi, Lin Yang

Abstract: The proliferation of saddle points, rather than poor local minima, is increasingly understood to be a primary obstacle in large-scale non-convex optimization for machine learning. Variable elimination algorithms, like Variable Projection (VarPro), have long been observed to exhibit superior convergence and robustness in practice, yet a principled understanding of why they so effectively navigate t… ▽ More The proliferation of saddle points, rather than poor local minima, is increasingly understood to be a primary obstacle in large-scale non-convex optimization for machine learning. Variable elimination algorithms, like Variable Projection (VarPro), have long been observed to exhibit superior convergence and robustness in practice, yet a principled understanding of why they so effectively navigate these complex energy landscapes has remained elusive. In this work, we provide a rigorous geometric explanation by comparing the optimization landscapes of the original and reduced formulations. Through a rigorous analysis based on Hessian inertia and the Schur complement, we prove that variable elimination fundamentally reshapes the critical point structure of the objective function, revealing that local maxima in the reduced landscape are created from, and correspond directly to, saddle points in the original formulation. Our findings are illustrated on the canonical problem of non-convex matrix factorization, visualized directly on two-parameter neural networks, and finally validated in training deep Residual Networks, where our approach yields dramatic improvements in stability and convergence to superior minima. This work goes beyond explaining an existing method; it establishes landscape simplification via saddle point transformation as a powerful principle that can guide the design of a new generation of more robust and efficient optimization algorithms. △ Less

Submitted 3 November, 2025; originally announced November 2025.

Reimagining Safety Alignment with An Image

Authors: Yifan Xia, Guorui Chen, Wenqian Yu, Zhijiang Li, Philip Torr, Jindong Gu

Abstract: Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated by the need to accommodate different value systems and precisely align with given safety preferences. Moreover, traditional methods like SFT and RLHF lack this… ▽ More Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated by the need to accommodate different value systems and precisely align with given safety preferences. Moreover, traditional methods like SFT and RLHF lack this capability due to their costly parameter tuning requirements and inability to support multiple value systems within a single model. These problems are more obvious in multimodal large language models (MLLMs), especially in terms of heightened over-refusal in cross-modal tasks and new security risks arising from expanded attack surfaces. We propose Magic Image, an optimization-driven visual prompt framework that enhances security while reducing over-refusal. By optimizing image prompts using harmful/benign samples, our method enables a single model to adapt to different value systems and better align with given safety preferences without parameter updates. Experiments demonstrate improved safety-effectiveness balance across diverse datasets while preserving model performance, offering a practical solution for deployable MLLM safety alignment. △ Less

Submitted 1 November, 2025; originally announced November 2025.

G2: Guided Generation for Enhanced Output Diversity in LLMs

Authors: Zhiwen Ruan, Yixia Li, Yefeng Liu, Yun Chen, Weihua Luo, Peng Li, Yang Liu, Guanhua Chen

Abstract: Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, these models exhibit a critical limitation in output diversity, often generating highly similar content across multiple attempts. This limitation significantly affects tasks requiring diverse outputs, from creative writing to reasoning. Existing solutions, like temperat… ▽ More Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, these models exhibit a critical limitation in output diversity, often generating highly similar content across multiple attempts. This limitation significantly affects tasks requiring diverse outputs, from creative writing to reasoning. Existing solutions, like temperature scaling, enhance diversity by modifying probability distributions but compromise output quality. We propose Guide-to-Generation (G2), a training-free plug-and-play method that enhances output diversity while preserving generation quality. G2 employs a base generator alongside dual Guides, which guide the generation process through decoding-based interventions to encourage more diverse outputs conditioned on the original query. Comprehensive experiments demonstrate that G2 effectively improves output diversity while maintaining an optimal balance between diversity and quality. △ Less

Submitted 1 November, 2025; originally announced November 2025.

Comments: EMNLP 2025

Meritocracy versus Matthew-effect: Two underlying network formation mechanisms of online social platforms

Authors: Yuchen Xu, Wenjun Mei, Ge Chen, Linyuan Lü

Abstract: With the rapid development of the internet industry, online social networks have come to play an increasingly significant role in everyday life. In recent years, content-based emerging platforms such as TikTok, Instagram, and Bilibili have diverged fundamentally in their underlying logic from traditional connection-based social platforms like Facebook and LinkedIn. Empirical data on follower count… ▽ More With the rapid development of the internet industry, online social networks have come to play an increasingly significant role in everyday life. In recent years, content-based emerging platforms such as TikTok, Instagram, and Bilibili have diverged fundamentally in their underlying logic from traditional connection-based social platforms like Facebook and LinkedIn. Empirical data on follower counts and follower-count-based rankings reveal that the distribution of social power varies significantly across different types of platforms, with content-based platforms exhibiting notably greater inequality. Here we propose two fundamental network formation mechanisms: a meritocracy-based model and a Matthew-effect-based model, designed to capture the formation logic underlying traditional and emerging social networks, respectively. Through theoretical and numerical analysis, we demonstrate that both models replicate salient statistical features of social networks including scale-free and small-world property, while also closely match empirical patterns on the relationship between in-degrees and in-degree rankings, thereby capturing the distinctive distributions of social power in respective platforms. Moreover, networks such as academic collaboration networks, where the distribution of social power usually lies between that of traditional and emerging platorms, can be interpreted through a hybrid of the two proposed mechanisms. Deconstructing the formation mechanisms of online social networks offers valuable insights into the evolution of the content ecosystems and the behavioral patterns of content creators on online social platforms. △ Less

Submitted 31 October, 2025; originally announced October 2025.

Comments: 11 pages, 4 figures

Kimi Linear: An Expressive, Efficient Attention Architecture

Authors: Kimi Team, Yu Zhang, Zongyu Lin, Xingcheng Yao, Jiaxi Hu, Fanqing Meng, Chengyin Liu, Xin Men, Songlin Yang, Zhiyuan Li, Wentao Li, Enzhe Lu, Weizhou Liu, Yanru Chen, Weixin Xu, Longhui Yu, Yejie Wang, Yu Fan, Longguang Zhong, Enming Yuan, Dehao Zhang, Yizhi Zhang, T. Y. Liu, Haiming Wang, Shengjun Fang , et al. (35 additional authors not shown)

Abstract: We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including short-context, long-context, and reinforcement learning (RL) scaling regimes. At its core lies Kimi Delta Attention (KDA), an expressive linear attention module that extends Gated DeltaNet with a finer-grained gating mech… ▽ More We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including short-context, long-context, and reinforcement learning (RL) scaling regimes. At its core lies Kimi Delta Attention (KDA), an expressive linear attention module that extends Gated DeltaNet with a finer-grained gating mechanism, enabling more effective use of limited finite-state RNN memory. Our bespoke chunkwise algorithm achieves high hardware efficiency through a specialized variant of the Diagonal-Plus-Low-Rank (DPLR) transition matrices, which substantially reduces computation compared to the general DPLR formulation while remaining more consistent with the classical delta rule. We pretrain a Kimi Linear model with 3B activated parameters and 48B total parameters, based on a layerwise hybrid of KDA and Multi-Head Latent Attention (MLA). Our experiments show that with an identical training recipe, Kimi Linear outperforms full MLA with a sizeable margin across all evaluated tasks, while reducing KV cache usage by up to 75% and achieving up to 6 times decoding throughput for a 1M context. These results demonstrate that Kimi Linear can be a drop-in replacement for full attention architectures with superior performance and efficiency, including tasks with longer input and output lengths. To support further research, we open-source the KDA kernel and vLLM implementations, and release the pre-trained and instruction-tuned model checkpoints. △ Less

Submitted 1 November, 2025; v1 submitted 30 October, 2025; originally announced October 2025.

Comments: Kimi Linear tech report

Mean-Shift Theory and Its Applications in Swarm Robotics: A New Way to Enhance the Efficiency of Multi-Robot Collaboration

Authors: Guibin Sun, Jinhu Lü, Kexin Liu, Zhenqian Wang, Guanrong Chen

Abstract: Swarms evolving from collective behaviors among multiple individuals are commonly seen in nature, which enables biological systems to exhibit more efficient and robust collaboration. Creating similar swarm intelligence in engineered robots poses challenges to the design of collaborative algorithms that can be programmed at large scales. The assignment-based method has played an eminent role for a… ▽ More Swarms evolving from collective behaviors among multiple individuals are commonly seen in nature, which enables biological systems to exhibit more efficient and robust collaboration. Creating similar swarm intelligence in engineered robots poses challenges to the design of collaborative algorithms that can be programmed at large scales. The assignment-based method has played an eminent role for a very long time in solving collaboration problems of robot swarms. However, it faces fundamental limitations in terms of efficiency and robustness due to its unscalability to swarm variants. This article presents a tutorial review on recent advances in assignment-free collaboration of robot swarms, focusing on the problem of shape formation. A key theoretical component is the recently developed \emph{mean-shift exploration} strategy, which improves the collaboration efficiency of large-scale swarms by dozens of times. Further, the efficiency improvement is more significant as the swarm scale increases. Finally, this article discusses three important applications of the mean-shift exploration strategy, including precise shape formation, area coverage formation, and maneuvering formation, as well as their corresponding industrial scenarios in smart warehousing, area exploration, and cargo transportation. △ Less

Submitted 7 November, 2025; v1 submitted 28 October, 2025; originally announced October 2025.

Tongyi DeepResearch Technical Report

Authors: Tongyi DeepResearch Team, Baixuan Li, Bo Zhang, Dingchu Zhang, Fei Huang, Guangyu Li, Guoxin Chen, Huifeng Yin, Jialong Wu, Jingren Zhou, Kuan Li, Liangcai Su, Litu Ou, Liwen Zhang, Pengjun Xie, Rui Ye, Wenbiao Yin, Xinmiao Yu, Xinyu Wang, Xixi Wu, Xuanzhong Chen, Yida Zhao, Zhen Zhang, Zhengwei Tao, Zhongwang Zhang , et al. (32 additional authors not shown)

Abstract: We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework that combines agentic mid-training and agentic post-training, enabling scalable reasoning and information seeking across co… ▽ More We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework that combines agentic mid-training and agentic post-training, enabling scalable reasoning and information seeking across complex tasks. We design a highly scalable data synthesis pipeline that is fully automatic, without relying on costly human annotation, and empowers all training stages. By constructing customized environments for each stage, our system enables stable and consistent interactions throughout. Tongyi DeepResearch, featuring 30.5 billion total parameters, with only 3.3 billion activated per token, achieves state-of-the-art performance across a range of agentic deep research benchmarks, including Humanity's Last Exam, BrowseComp, BrowseComp-ZH, WebWalkerQA, xbench-DeepSearch, FRAMES and xbench-DeepSearch-2510. We open-source the model, framework, and complete solutions to empower the community. △ Less

Submitted 4 November, 2025; v1 submitted 28 October, 2025; originally announced October 2025.

Comments: https://tongyi-agent.github.io/blog

AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis

Authors: Xuanzhong Chen, Zile Qiao, Guoxin Chen, Liangcai Su, Zhen Zhang, Xinyu Wang, Pengjun Xie, Fei Huang, Jingren Zhou, Yong Jiang

Abstract: Training large language model agents on tasks at the frontier of their capabilities is key to unlocking advanced reasoning. We introduce a data synthesis approach inspired by the educational theory of the Zone of Proximal Development (ZPD), which defines this frontier as tasks an LLM cannot solve alone but can master with guidance. To operationalize this, we present the AgentFrontier Engine, an au… ▽ More Training large language model agents on tasks at the frontier of their capabilities is key to unlocking advanced reasoning. We introduce a data synthesis approach inspired by the educational theory of the Zone of Proximal Development (ZPD), which defines this frontier as tasks an LLM cannot solve alone but can master with guidance. To operationalize this, we present the AgentFrontier Engine, an automated pipeline that synthesizes high-quality, multidisciplinary data situated precisely within the LLM's ZPD. This engine supports both continued pre-training with knowledge-intensive data and targeted post-training on complex reasoning tasks. From the same framework, we derive the ZPD Exam, a dynamic and automated benchmark designed to evaluate agent capabilities on these frontier tasks. We train AgentFrontier-30B-A3B model on our synthesized data, which achieves state-of-the-art results on demanding benchmarks like Humanity's Last Exam, even surpassing some leading proprietary agents. Our work demonstrates that a ZPD-guided approach to data synthesis offers a scalable and effective path toward building more capable LLM agents. △ Less

Submitted 28 October, 2025; originally announced October 2025.

Comments: https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research/

ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization

Authors: Guoxin Chen, Jing Wu, Xinjie Chen, Wayne Xin Zhao, Ruihua Song, Chengxi Li, Kai Fan, Dayiheng Liu, Minpeng Liao

Abstract: Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models can generate syntactically correct formal statements, they often fail to preserve the original problem's semantic intent. This limitation arises from the LLM app… ▽ More Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models can generate syntactically correct formal statements, they often fail to preserve the original problem's semantic intent. This limitation arises from the LLM approaches' treating autoformalization as a simplistic translation task which lacks mechanisms for self-reflection and iterative refinement that human experts naturally employ. To address these issues, we propose ReForm, a Reflective Autoformalization method that tightly integrates semantic consistency evaluation into the autoformalization process. This enables the model to iteratively generate formal statements, assess its semantic fidelity, and self-correct identified errors through progressive refinement. To effectively train this reflective model, we introduce Prospective Bounded Sequence Optimization (PBSO), which employs different rewards at different sequence positions to ensure that the model develops both accurate autoformalization and correct semantic validations, preventing superficial critiques that would undermine the purpose of reflection. Extensive experiments across four autoformalization benchmarks demonstrate that ReForm achieves an average improvement of 22.6 percentage points over the strongest baselines. To further ensure evaluation reliability, we introduce ConsistencyCheck, a benchmark of 859 expert-annotated items that not only validates LLMs as judges but also reveals that autoformalization is inherently difficult: even human experts produce semantic errors in up to 38.5% of cases. △ Less

Submitted 30 October, 2025; v1 submitted 28 October, 2025; originally announced October 2025.

Comments: https://github.com/Chen-GX/ReForm

Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives

Authors: Gang Chen, Changshuo Liu, Gene Anne Ooi, Marcus Tan, Zhongle Xie, Jianwei Yin, James Wei Luen Yip, Wenqiao Zhang, Jiaqi Zhu, Beng Chin Ooi

Abstract: Generative Artificial Intelligence (GenAI) is taking the world by storm. It promises transformative opportunities for advancing and disrupting existing practices, including healthcare. From large language models (LLMs) for clinical note synthesis and conversational assistance to multimodal systems that integrate medical imaging, electronic health records, and genomic data for decision support, Gen… ▽ More Generative Artificial Intelligence (GenAI) is taking the world by storm. It promises transformative opportunities for advancing and disrupting existing practices, including healthcare. From large language models (LLMs) for clinical note synthesis and conversational assistance to multimodal systems that integrate medical imaging, electronic health records, and genomic data for decision support, GenAI is transforming the practice of medicine and the delivery of healthcare, such as diagnosis and personalized treatments, with great potential in reducing the cognitive burden on clinicians, thereby improving overall healthcare delivery. However, GenAI deployment in healthcare requires an in-depth understanding of healthcare tasks and what can and cannot be achieved. In this paper, we propose a data-centric paradigm in the design and deployment of GenAI systems for healthcare. Specifically, we reposition the data life cycle by making the medical data ecosystem as the foundational substrate for generative healthcare systems. This ecosystem is designed to sustainably support the integration, representation, and retrieval of diverse medical data and knowledge. With effective and efficient data processing pipelines, such as semantic vector search and contextual querying, it enables GenAI-powered operations for upstream model components and downstream clinical applications. Ultimately, it not only supplies foundation models with high-quality, multimodal data for large-scale pretraining and domain-specific fine-tuning, but also serves as a knowledge retrieval backend to support task-specific inference via the agentic layer. The ecosystem enables the deployment of GenAI for high-quality and effective healthcare delivery. △ Less

Submitted 28 October, 2025; originally announced October 2025.

EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT

Authors: Baoqi Pei, Yifei Huang, Jilan Xu, Yuping He, Guo Chen, Fei Wu, Yu Qiao, Jiangmiao Pang

Abstract: Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current multimodal large language models MLLMs, which excel at visible event reasoning but lack embodied, first-person understanding. To bridge this gap, we introduce E… ▽ More Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current multimodal large language models MLLMs, which excel at visible event reasoning but lack embodied, first-person understanding. To bridge this gap, we introduce EgoThinker, a novel framework that endows MLLMs with robust egocentric reasoning capabilities through spatio-temporal chain-of-thought supervision and a two-stage learning curriculum. First, we introduce EgoRe-5M, a large-scale egocentric QA dataset constructed from 13M diverse egocentric video clips. This dataset features multi-minute segments annotated with detailed CoT rationales and dense hand-object grounding. Second, we employ SFT on EgoRe-5M to instill reasoning skills, followed by reinforcement fine-tuning RFT to further enhance spatio-temporal localization. Experimental results show that EgoThinker outperforms existing methods across multiple egocentric benchmarks, while achieving substantial improvements in fine-grained spatio-temporal localization tasks. Full code and data are released at https://github.com/InternRobotics/EgoThinker. △ Less

Submitted 27 October, 2025; originally announced October 2025.

Comments: Accepted at NeurIPS 2025

Multi-Task Surrogate-Assisted Search with Bayesian Competitive Knowledge Transfer for Expensive Optimization

Authors: Yi Lu, Xiaoming Xue, Kai Zhang, Liming Zhang, Guodong Chen, Chenming Cao, Piyang Liu, Kay Chen Tan

Abstract: Expensive optimization problems (EOPs) present significant challenges for traditional evolutionary optimization due to their limited evaluation calls. Although surrogate-assisted search (SAS) has become a popular paradigm for addressing EOPs, it still suffers from the cold-start issue. In response to this challenge, knowledge transfer has been gaining popularity for its ability to leverage search… ▽ More Expensive optimization problems (EOPs) present significant challenges for traditional evolutionary optimization due to their limited evaluation calls. Although surrogate-assisted search (SAS) has become a popular paradigm for addressing EOPs, it still suffers from the cold-start issue. In response to this challenge, knowledge transfer has been gaining popularity for its ability to leverage search experience from potentially related instances, ultimately facilitating head-start optimization for more efficient decision-making. However, the curse of negative transfer persists when applying knowledge transfer to EOPs, primarily due to the inherent limitations of existing methods in assessing knowledge transferability. On the one hand, a priori transferability assessment criteria are intrinsically inaccurate due to their imprecise understandings. On the other hand, a posteriori methods often necessitate sufficient observations to make correct inferences, rendering them inefficient when applied to EOPs. Considering the above, this paper introduces a Bayesian competitive knowledge transfer (BCKT) method developed to improve multi-task SAS (MSAS) when addressing multiple EOPs simultaneously. Specifically, the transferability of knowledge is estimated from a Bayesian perspective that accommodates both prior beliefs and empirical evidence, enabling accurate competition between inner-task and inter-task solutions, ultimately leading to the adaptive use of promising solutions while effectively suppressing inferior ones. The effectiveness of our method in boosting various SAS algorithms for both multi-task and many-task problems is empirically validated, complemented by comparative studies that demonstrate its superiority over peer algorithms and its applicability to real-world scenarios. The source code of our method is available at https://github.com/XmingHsueh/MSAS-BCKT. △ Less

Submitted 27 October, 2025; originally announced October 2025.

DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling

Authors: Hao Sun, Zile Qiao, Bo Wang, Guoxin Chen, Yingyan Hou, Yong Jiang, Pengjun Xie, Fei Huang, Yan Zhang

Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dynamic integration of external knowledge. To further improve RAG's flexibility, Agentic RAG introduces autonomous agents into the workflow. However, Agentic RAG faces several challenges: (1) the success of each step depends on both high-quality planning and acc… ▽ More Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dynamic integration of external knowledge. To further improve RAG's flexibility, Agentic RAG introduces autonomous agents into the workflow. However, Agentic RAG faces several challenges: (1) the success of each step depends on both high-quality planning and accurate search, (2) the lack of supervision for intermediate reasoning steps, and (3) the exponentially large candidate space for planning and searching. To address these challenges, we propose DecoupleSearch, a novel framework that decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. Our approach constructs a reasoning tree, where each node represents planning and search steps. We leverage Monte Carlo Tree Search to assess the quality of each step. During inference, Hierarchical Beam Search iteratively refines planning and search candidates with dual value models. Extensive experiments across policy models of varying parameter sizes, demonstrate the effectiveness of our method. △ Less

Submitted 7 September, 2025; originally announced October 2025.

Comments: EMNLP 2025 Main Conference

Privacy Guarantee for Nash Equilibrium Computation of Aggregative Games Based on Pointwise Maximal Leakage

Authors: Zhaoyang Cheng, Guanpu Chen, Tobias J. Oechtering, Mikael Skoglund

Abstract: Privacy preservation has served as a key metric in designing Nash equilibrium (NE) computation algorithms. Although differential privacy (DP) has been widely employed for privacy guarantees, it does not exploit prior distributional knowledge of datasets and is ineffective in assessing information leakage for correlated datasets. To address these concerns, we establish a pointwise maximal leakage (… ▽ More Privacy preservation has served as a key metric in designing Nash equilibrium (NE) computation algorithms. Although differential privacy (DP) has been widely employed for privacy guarantees, it does not exploit prior distributional knowledge of datasets and is ineffective in assessing information leakage for correlated datasets. To address these concerns, we establish a pointwise maximal leakage (PML) framework when computing NE in aggregative games. By incorporating prior knowledge of players' cost function datasets, we obtain a precise and computable upper bound of privacy leakage with PML guarantees. In the entire view, we show PML refines DP by offering a tighter privacy guarantee, enabling flexibility in designing NE computation. Also, in the individual view, we reveal that the lower bound of PML can exceed the upper bound of DP by constructing specific correlated datasets. The results emphasize that PML is a more proper privacy measure than DP since the latter fails to adequately capture privacy leakage in correlated datasets. Moreover, we conduct experiments with adversaries who attempt to infer players' private information to illustrate the effectiveness of our framework. △ Less

Submitted 24 October, 2025; originally announced October 2025.

DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services

Authors: Xiang Li, Huizi Yu, Wenkong Wang, Yiran Wu, Jiayan Zhou, Wenyue Hua, Xinxin Lin, Wenjia Tan, Lexuan Zhu, Bingyi Chen, Guang Chen, Ming-Li Chen, Yang Zhou, Zhao Li, Themistocles L. Assimes, Yongfeng Zhang, Qingyun Wu, Xin Ma, Lingyao Li, Lizhou Fan

Abstract: Objective: Emergency medical dispatch (EMD) is a high-stakes process challenged by caller distress, ambiguity, and cognitive load. Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers. This study aimed to develop and evaluate a taxonomy-grounded, LLM-powered multi-agent system for simulating realistic EMD scenarios. Methods: We constructed a clinica… ▽ More Objective: Emergency medical dispatch (EMD) is a high-stakes process challenged by caller distress, ambiguity, and cognitive load. Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers. This study aimed to develop and evaluate a taxonomy-grounded, LLM-powered multi-agent system for simulating realistic EMD scenarios. Methods: We constructed a clinical taxonomy (32 chief complaints, 6 caller identities from MIMIC-III) and a six-phase call protocol. Using this framework, we developed an AutoGen-based MAS with Caller and Dispatcher Agents. The system grounds interactions in a fact commons to ensure clinical plausibility and mitigate misinformation. We used a hybrid evaluation framework: four physicians assessed 100 simulated cases for "Guidance Efficacy" and "Dispatch Effectiveness," supplemented by automated linguistic analysis (sentiment, readability, politeness). Results: Human evaluation, with substantial inter-rater agreement (Gwe's AC1 > 0.70), confirmed the system's high performance. It demonstrated excellent Dispatch Effectiveness (e.g., 94 % contacting the correct potential other agents) and Guidance Efficacy (advice provided in 91 % of cases), both rated highly by physicians. Algorithmic metrics corroborated these findings, indicating a predominantly neutral affective profile (73.7 % neutral sentiment; 90.4 % neutral emotion), high readability (Flesch 80.9), and a consistently polite style (60.0 % polite; 0 % impolite). Conclusion: Our taxonomy-grounded MAS simulates diverse, clinically plausible dispatch scenarios with high fidelity. Findings support its use for dispatcher training, protocol evaluation, and as a foundation for real-time decision support. This work outlines a pathway for safely integrating advanced AI agents into emergency response workflows. △ Less

Submitted 24 October, 2025; originally announced October 2025.

Comments: 27 pages, 7 figures, 3 tables

MSC Class: 68T07; 92C50 ACM Class: I.2.7; J.3

R2-SVC: Towards Real-World Robust and Expressive Zero-shot Singing Voice Conversion

Authors: Junjie Zheng, Gongyu Chen, Chaofan Ding, Zihao Chen

Abstract: In real-world singing voice conversion (SVC) applications, environmental noise and the demand for expressive output pose significant challenges. Conventional methods, however, are typically designed without accounting for real deployment scenarios, as both training and inference usually rely on clean data. This mismatch hinders practical use, given the inevitable presence of diverse noise sources… ▽ More In real-world singing voice conversion (SVC) applications, environmental noise and the demand for expressive output pose significant challenges. Conventional methods, however, are typically designed without accounting for real deployment scenarios, as both training and inference usually rely on clean data. This mismatch hinders practical use, given the inevitable presence of diverse noise sources and artifacts from music separation. To tackle these issues, we propose R2-SVC, a robust and expressive SVC framework. First, we introduce simulation-based robustness enhancement through random fundamental frequency ($F_0$) perturbations and music separation artifact simulations (e.g., reverberation, echo), substantially improving performance under noisy conditions. Second, we enrich speaker representation using domain-specific singing data: alongside clean vocals, we incorporate DNSMOS-filtered separated vocals and public singing corpora, enabling the model to preserve speaker timbre while capturing singing style nuances. Third, we integrate the Neural Source-Filter (NSF) model to explicitly represent harmonic and noise components, enhancing the naturalness and controllability of converted singing. R2-SVC achieves state-of-the-art results on multiple SVC benchmarks under both clean and noisy conditions. △ Less

Submitted 23 October, 2025; originally announced October 2025.

Comments: 5 pages, 2 figures

Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data

Authors: Shuli Zhang, Hao Zhou, Jiaqi Zheng, Guibin Jiang, Bing Cheng, Wei Lin, Guihai Chen

Abstract: Online Internet platforms require sophisticated marketing strategies to optimize user retention and platform revenue -- a classical resource allocation problem. Traditional solutions adopt a two-stage pipeline: machine learning (ML) for predicting individual treatment effects to marketing actions, followed by operations research (OR) optimization for decision-making. This paradigm presents two fun… ▽ More Online Internet platforms require sophisticated marketing strategies to optimize user retention and platform revenue -- a classical resource allocation problem. Traditional solutions adopt a two-stage pipeline: machine learning (ML) for predicting individual treatment effects to marketing actions, followed by operations research (OR) optimization for decision-making. This paradigm presents two fundamental technical challenges. First, the prediction-decision misalignment: Conventional ML methods focus solely on prediction accuracy without considering downstream optimization objectives, leading to improved predictive metrics that fail to translate to better decisions. Second, the bias-variance dilemma: Observational data suffers from multiple biases (e.g., selection bias, position bias), while experimental data (e.g., randomized controlled trials), though unbiased, is typically scarce and costly -- resulting in high-variance estimates. We propose Bi-level Decision-Focused Causal Learning (Bi-DFCL) that systematically addresses these challenges. First, we develop an unbiased estimator of OR decision quality using experimental data, which guides ML model training through surrogate loss functions that bridge discrete optimization gradients. Second, we establish a bi-level optimization framework that jointly leverages observational and experimental data, solved via implicit differentiation. This novel formulation enables our unbiased OR estimator to correct learning directions from biased observational data, achieving optimal bias-variance tradeoff. Extensive evaluations on public benchmarks, industrial marketing datasets, and large-scale online A/B tests demonstrate the effectiveness of Bi-DFCL, showing statistically significant improvements over state-of-the-art. Currently, Bi-DFCL has been deployed at Meituan, one of the largest online food delivery platforms in the world. △ Less

Submitted 22 October, 2025; originally announced October 2025.

Comments: Accepted by NeurIPS 2025

Continual Knowledge Adaptation for Reinforcement Learning

Authors: Jinwu Hu, Zihao Lian, Zhiquan Wen, Chenghao Li, Guohao Chen, Xutao Wen, Bin Xiao, Mingkui Tan

Abstract: Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks and changing conditions. Although Continual Reinforcement Learning facilitates learning across multiple tasks, existing methods often suffer from catastrophic forgetting and ineffi… ▽ More Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks and changing conditions. Although Continual Reinforcement Learning facilitates learning across multiple tasks, existing methods often suffer from catastrophic forgetting and inefficient knowledge utilization. To address these challenges, we propose Continual Knowledge Adaptation for Reinforcement Learning (CKA-RL), which enables the accumulation and effective utilization of historical knowledge. Specifically, we introduce a Continual Knowledge Adaptation strategy, which involves maintaining a task-specific knowledge vector pool and dynamically using historical knowledge to adapt the agent to new tasks. This process mitigates catastrophic forgetting and enables efficient knowledge transfer across tasks by preserving and adapting critical model parameters. Additionally, we propose an Adaptive Knowledge Merging mechanism that combines similar knowledge vectors to address scalability challenges, reducing memory requirements while ensuring the retention of essential knowledge. Experiments on three benchmarks demonstrate that the proposed CKA-RL outperforms state-of-the-art methods, achieving an improvement of 4.20% in overall performance and 8.02% in forward transfer. The source code is available at https://github.com/Fhujinwu/CKA-RL. △ Less

Submitted 22 October, 2025; originally announced October 2025.

Comments: NeurIPS 2025

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

Authors: Kai Zeng, Zhanqian Wu, Kaixin Xiong, Xiaobao Wei, Xiangyu Guo, Zhenxin Zhu, Kalok Ho, Lijun Zhou, Bohan Zeng, Ming Lu, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye, Wentao Zhang

Abstract: Recent advancements in driving world models enable controllable generation of high-quality RGB videos or multimodal videos. Existing methods primarily focus on metrics related to generation quality and controllability. However, they often overlook the evaluation of downstream perception tasks, which are $\mathbf{really\ crucial}$ for the performance of autonomous driving. Existing methods usually… ▽ More Recent advancements in driving world models enable controllable generation of high-quality RGB videos or multimodal videos. Existing methods primarily focus on metrics related to generation quality and controllability. However, they often overlook the evaluation of downstream perception tasks, which are $\mathbf{really\ crucial}$ for the performance of autonomous driving. Existing methods usually leverage a training strategy that first pretrains on synthetic data and finetunes on real data, resulting in twice the epochs compared to the baseline (real data only). When we double the epochs in the baseline, the benefit of synthetic data becomes negligible. To thoroughly demonstrate the benefit of synthetic data, we introduce Dream4Drive, a novel synthetic data generation framework designed for enhancing the downstream perception tasks. Dream4Drive first decomposes the input video into several 3D-aware guidance maps and subsequently renders the 3D assets onto these guidance maps. Finally, the driving world model is fine-tuned to produce the edited, multi-view photorealistic videos, which can be used to train the downstream perception models. Dream4Drive enables unprecedented flexibility in generating multi-view corner cases at scale, significantly boosting corner case perception in autonomous driving. To facilitate future research, we also contribute a large-scale 3D asset dataset named DriveObj3D, covering the typical categories in driving scenarios and enabling diverse 3D-aware video editing. We conduct comprehensive experiments to show that Dream4Drive can effectively boost the performance of downstream perception models under various training epochs. Page: https://wm-research.github.io/Dream4Drive/ GitHub Link: https://github.com/wm-research/Dream4Drive △ Less

Submitted 24 October, 2025; v1 submitted 21 October, 2025; originally announced October 2025.

ViSE: A Systematic Approach to Vision-Only Street-View Extrapolation

Authors: Kaiyuan Tan, Yingying Shen, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye

Abstract: Realistic view extrapolation is critical for closed-loop simulation in autonomous driving, yet it remains a significant challenge for current Novel View Synthesis (NVS) methods, which often produce distorted and inconsistent images beyond the original trajectory. This report presents our winning solution which ctook first place in the RealADSim Workshop NVS track at ICCV 2025. To address the core… ▽ More Realistic view extrapolation is critical for closed-loop simulation in autonomous driving, yet it remains a significant challenge for current Novel View Synthesis (NVS) methods, which often produce distorted and inconsistent images beyond the original trajectory. This report presents our winning solution which ctook first place in the RealADSim Workshop NVS track at ICCV 2025. To address the core challenges of street view extrapolation, we introduce a comprehensive four-stage pipeline. First, we employ a data-driven initialization strategy to generate a robust pseudo-LiDAR point cloud, avoiding local minima. Second, we inject strong geometric priors by modeling the road surface with a novel dimension-reduced SDF termed 2D-SDF. Third, we leverage a generative prior to create pseudo ground truth for extrapolated viewpoints, providing auxilary supervision. Finally, a data-driven adaptation network removes time-specific artifacts. On the RealADSim-NVS benchmark, our method achieves a final score of 0.441, ranking first among all participants. △ Less

Submitted 21 October, 2025; originally announced October 2025.

Towards Identifiability of Hierarchical Temporal Causal Representation Learning

Authors: Zijian Li, Minghao Fu, Junxian Huang, Yifan Shen, Ruichu Cai, Yuewen Sun, Guangyi Chen, Kun Zhang

Abstract: Modeling hierarchical latent dynamics behind time series data is critical for capturing temporal dependencies across multiple levels of abstraction in real-world tasks. However, existing temporal causal representation learning methods fail to capture such dynamics, as they fail to recover the joint distribution of hierarchical latent variables from \textit{single-timestep observed variables}. Inte… ▽ More Modeling hierarchical latent dynamics behind time series data is critical for capturing temporal dependencies across multiple levels of abstraction in real-world tasks. However, existing temporal causal representation learning methods fail to capture such dynamics, as they fail to recover the joint distribution of hierarchical latent variables from \textit{single-timestep observed variables}. Interestingly, we find that the joint distribution of hierarchical latent variables can be uniquely determined using three conditionally independent observations. Building on this insight, we propose a Causally Hierarchical Latent Dynamic (CHiLD) identification framework. Our approach first employs temporal contextual observed variables to identify the joint distribution of multi-layer latent variables. Sequentially, we exploit the natural sparsity of the hierarchical structure among latent variables to identify latent variables within each layer. Guided by the theoretical results, we develop a time series generative model grounded in variational inference. This model incorporates a contextual encoder to reconstruct multi-layer latent variables and normalize flow-based hierarchical prior networks to impose the independent noise condition of hierarchical latent dynamics. Empirical evaluations on both synthetic and real-world datasets validate our theoretical claims and demonstrate the effectiveness of CHiLD in modeling hierarchical latent dynamics. △ Less

Submitted 21 October, 2025; originally announced October 2025.

Online Time Series Forecasting with Theoretical Guarantees

Authors: Zijian Li, Changze Zhou, Minghao Fu, Sanjay Manjunath, Fan Feng, Guangyi Chen, Yingyao Hu, Ruichu Cai, Kun Zhang

Abstract: This paper is concerned with online time series forecasting, where unknown distribution shifts occur over time, i.e., latent variables influence the mapping from historical to future observations. To develop an automated way of online time series forecasting, we propose a Theoretical framework for Online Time-series forecasting (TOT in short) with theoretical guarantees. Specifically, we prove tha… ▽ More This paper is concerned with online time series forecasting, where unknown distribution shifts occur over time, i.e., latent variables influence the mapping from historical to future observations. To develop an automated way of online time series forecasting, we propose a Theoretical framework for Online Time-series forecasting (TOT in short) with theoretical guarantees. Specifically, we prove that supplying a forecaster with latent variables tightens the Bayes risk, the benefit endures under estimation uncertainty of latent variables and grows as the latent variables achieve a more precise identifiability. To better introduce latent variables into online forecasting algorithms, we further propose to identify latent variables with minimal adjacent observations. Based on these results, we devise a model-agnostic blueprint by employing a temporal decoder to match the distribution of observed variables and two independent noise estimators to model the causal inference of latent variables and mixing procedures of observed variables, respectively. Experiment results on synthetic data support our theoretical claims. Moreover, plug-in implementations built on several baselines yield general improvement across multiple benchmarks, highlighting the effectiveness in real-world applications. △ Less

Submitted 21 October, 2025; originally announced October 2025.

PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception

Authors: Kaichen Zhou, Yuhan Wang, Grace Chen, Xinhai Chang, Gaspard Beaudouin, Fangneng Zhan, Paul Pu Liang, Mengyu Wang

Abstract: Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models often struggle in real-world scenarios involving complex dynamic elements, such as moving humans or deformable objects like umbrellas. To address this limitation,… ▽ More Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models often struggle in real-world scenarios involving complex dynamic elements, such as moving humans or deformable objects like umbrellas. To address this limitation, we introduce PAGE-4D, a feedforward model that extends VGGT to dynamic scenes, enabling camera pose estimation, depth prediction, and point cloud reconstruction -- all without post-processing. A central challenge in multi-task 4D reconstruction is the inherent conflict between tasks: accurate camera pose estimation requires suppressing dynamic regions, while geometry reconstruction requires modeling them. To resolve this tension, we propose a dynamics-aware aggregator that disentangles static and dynamic information by predicting a dynamics-aware mask -- suppressing motion cues for pose estimation while amplifying them for geometry reconstruction. Extensive experiments show that PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction. △ Less

Submitted 21 October, 2025; v1 submitted 20 October, 2025; originally announced October 2025.

CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs

Authors: Gucongcong Fan, Chaoyue Niu, Chengfei Lyu, Fan Wu, Guihai Chen

Abstract: Mobile agents rely on Large Language Models (LLMs) to plan and execute tasks on smartphone user interfaces (UIs). While cloud-based LLMs achieve high task accuracy, they require uploading the full UI state at every step, exposing unnecessary and often irrelevant information. In contrast, local LLMs avoid UI uploads but suffer from limited capacity, resulting in lower task success rates. We propose… ▽ More Mobile agents rely on Large Language Models (LLMs) to plan and execute tasks on smartphone user interfaces (UIs). While cloud-based LLMs achieve high task accuracy, they require uploading the full UI state at every step, exposing unnecessary and often irrelevant information. In contrast, local LLMs avoid UI uploads but suffer from limited capacity, resulting in lower task success rates. We propose $\textbf{CORE}$, a $\textbf{CO}$llaborative framework that combines the strengths of cloud and local LLMs to $\textbf{R}$educe UI $\textbf{E}$xposure, while maintaining task accuracy for mobile agents. CORE comprises three key components: (1) $\textbf{Layout-aware block partitioning}$, which groups semantically related UI elements based on the XML screen hierarchy; (2) $\textbf{Co-planning}$, where local and cloud LLMs collaboratively identify the current sub-task; and (3) $\textbf{Co-decision-making}$, where the local LLM ranks relevant UI blocks, and the cloud LLM selects specific UI elements within the top-ranked block. CORE further introduces a multi-round accumulation mechanism to mitigate local misjudgment or limited context. Experiments across diverse mobile apps and tasks show that CORE reduces UI exposure by up to 55.6% while maintaining task success rates slightly below cloud-only agents, effectively mitigating unnecessary privacy exposure to the cloud. The code is available at https://github.com/Entropy-Fighter/CORE. △ Less

Submitted 17 October, 2025; originally announced October 2025.

Rotatable Antenna Meets UAV: Towards Dual-Level Channel Reconfiguration Paradigm for ISAC

Authors: Shiying Chen, Guangji Chen, Long Shi, Qingqing Wu, Kang Wei

Abstract: Integrated sensing and communication (ISAC) is viewed as a key enabler for future wireless networks by sharing the hardware and wireless resources between the functionalities of sensing and communication (S&C). Due to the shared wireless resources for both S&C, it is challenging to achieve a critical trade-off between these two integrated functionalities. To address this issue, this paper proposes… ▽ More Integrated sensing and communication (ISAC) is viewed as a key enabler for future wireless networks by sharing the hardware and wireless resources between the functionalities of sensing and communication (S&C). Due to the shared wireless resources for both S&C, it is challenging to achieve a critical trade-off between these two integrated functionalities. To address this issue, this paper proposes a novel dual-level channel reconfiguration framework for ISAC by deploying rotatable antennas at an unmanned aerial vehicle (UAV), where both the large-scale path loss and the correlation of S&C channels can be proactively controlled, thereby allowing a flexible trade-off between S&C performance. To characterize the S&C tradeoff, we aim to maximize the communication rate by jointly optimizing the RA rotation, the transmit beamforming, and the UAV trajectory, subject to the given requirement of sensing performance. For the typical scenario of static UAV deployment, we introduce the concept of subspace correlation coefficient to derive closed-form solutions for the optimal RA rotation, transmit beamforming, and UAV hovering location. For the scenario of a fully mobile UAV, we prove that the optimal trajectory of a UAV follows a hover-fly-hover (HFH) structure, thereby obtaining its global optimal solution. Simulation results show that the proposed design significantly improves the achievable S&C trade-off region compared to benchmark schemes. △ Less

Submitted 17 October, 2025; originally announced October 2025.

Comments: 5 pages

LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models

Authors: Xiaohan Zhao, Hongyu Xiang, Shengze Ye, Song Li, Zhengkun Tian, Guanyu Chen, Ke Ding, Guanglu Wan

Abstract: This paper presents LongCat-Audio-Codec, an audio tokenizer and detokenizer solution designed for industrial grade end-to-end speech large language models. By leveraging a decoupled model architecture and a multistage training strategy, LongCat-Audio-Codec exhibits robust semantic modeling capabilities, flexible acoustic feature extraction capabilities, and low-latency streaming synthesis capabili… ▽ More This paper presents LongCat-Audio-Codec, an audio tokenizer and detokenizer solution designed for industrial grade end-to-end speech large language models. By leveraging a decoupled model architecture and a multistage training strategy, LongCat-Audio-Codec exhibits robust semantic modeling capabilities, flexible acoustic feature extraction capabilities, and low-latency streaming synthesis capabilities. It encodes speech at an ultra-low frame rate of 16.67 Hz, with a minimum bitrate of 0.43 kbps and a maximum bitrate of 0.87 kbps. Evaluation results demonstrate that LongCat-Audio-Codec achieves strong speech intelligibility and is capable of synthesizing highquality speech at low bitrate, thus effectively balancing coding efficiency and decoding quality. The inference code and model checkpoints of LongCat-Audio-Codec are available at: https://github.com/meituan-longcat/LongCat-Audio-Codec. △ Less

Submitted 16 October, 2025; originally announced October 2025.

Reflections from Research Roundtables at the Conference on Health, Inference, and Learning (CHIL) 2025

Authors: Emily Alsentzer, Marie-Laure Charpignon, Bill Chen, Niharika D'Souza, Jason Fries, Yixing Jiang, Aparajita Kashyap, Chanwoo Kim, Simon Lee, Aishwarya Mandyam, Ashery Mbilinyi, Nikita Mehandru, Nitish Nagesh, Brighton Nuwagira, Emma Pierson, Arvind Pillai, Akane Sano, Tanveer Syeda-Mahmood, Shashank Yadav, Elias Adhanom, Muhammad Umar Afza, Amelia Archer, Suhana Bedi, Vasiliki Bikia, Trenton Chang , et al. (68 additional authors not shown)

Abstract: The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025, at the University of California, Berkeley, in Berkeley, California, USA. As part of this year's program, we hosted Research Roundtables to catalyze collaborative, small-group dialogue around critical, timely topics at… ▽ More The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025, at the University of California, Berkeley, in Berkeley, California, USA. As part of this year's program, we hosted Research Roundtables to catalyze collaborative, small-group dialogue around critical, timely topics at the intersection of machine learning and healthcare. Each roundtable was moderated by a team of senior and junior chairs who fostered open exchange, intellectual curiosity, and inclusive engagement. The sessions emphasized rigorous discussion of key challenges, exploration of emerging opportunities, and collective ideation toward actionable directions in the field. In total, eight roundtables were held by 19 roundtable chairs on topics of "Explainability, Interpretability, and Transparency," "Uncertainty, Bias, and Fairness," "Causality," "Domain Adaptation," "Foundation Models," "Learning from Small Medical Data," "Multimodal Methods," and "Scalable, Translational Healthcare Solutions." △ Less

Submitted 3 November, 2025; v1 submitted 16 October, 2025; originally announced October 2025.