Showing 1–50 of 624 results for author: Cheng, H

Data-Driven MPC with Data Selection for Flexible Cable-Driven Robotic Arms

Authors: Huayue Liang, Yanbo Chen, Hongyang Cheng, Yanzhao Yu, Shoujie Li, Junbo Tan, Xueqian Wang, Long Zeng

Abstract: Flexible cable-driven robotic arms (FCRAs) offer dexterous and compliant motion. Still, the inherent properties of cables, such as resilience, hysteresis, and friction, often lead to particular difficulties in modeling and control. This paper proposes a model predictive control (MPC) method that relies exclusively on input-output data, without a physical model, to improve the control accuracy of F… ▽ More Flexible cable-driven robotic arms (FCRAs) offer dexterous and compliant motion. Still, the inherent properties of cables, such as resilience, hysteresis, and friction, often lead to particular difficulties in modeling and control. This paper proposes a model predictive control (MPC) method that relies exclusively on input-output data, without a physical model, to improve the control accuracy of FCRAs. First, we develop an implicit model based on input-output data and integrate it into an MPC optimization framework. Second, a data selection algorithm (DSA) is introduced to filter the data that best characterize the system, thereby reducing the solution time per step to approximately 4 ms, which is an improvement of nearly 80%. Lastly, the influence of hyperparameters on tracking error is investigated through simulation. The proposed method has been validated on a real FCRA platform, including five-point positioning accuracy tests, a five-point response tracking test, and trajectory tracking for letter drawing. The results demonstrate that the average positioning accuracy is approximately 2.070 mm. Moreover, compared to the PID method with an average tracking error of 1.418°, the proposed method achieves an average tracking error of 0.541°. △ Less

Submitted 21 July, 2025; originally announced July 2025.

Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation

Authors: Hengyu Zhang, Chunxu Shen, Xiangguo Sun, Jie Tan, Yanchao Tan, Yu Rong, Hong Cheng, Lingling Yi

Abstract: In real-world recommendation scenarios, users typically engage with platforms through multiple types of behavioral interactions. Multi-behavior recommendation algorithms aim to leverage various auxiliary user behaviors to enhance prediction for target behaviors of primary interest (e.g., buy), thereby overcoming performance limitations caused by data sparsity in target behavior records. Current st… ▽ More In real-world recommendation scenarios, users typically engage with platforms through multiple types of behavioral interactions. Multi-behavior recommendation algorithms aim to leverage various auxiliary user behaviors to enhance prediction for target behaviors of primary interest (e.g., buy), thereby overcoming performance limitations caused by data sparsity in target behavior records. Current state-of-the-art approaches typically employ hierarchical design following either cascading (e.g., view$\rightarrow$cart$\rightarrow$buy) or parallel (unified$\rightarrow$behavior$\rightarrow$specific components) paradigms, to capture behavioral relationships. However, these methods still face two critical challenges: (1) severe distribution disparities across behaviors, and (2) negative transfer effects caused by noise in auxiliary behaviors. In this paper, we propose a novel model-agnostic Hierarchical Graph Information Bottleneck (HGIB) framework for multi-behavior recommendation to effectively address these challenges. Following information bottleneck principles, our framework optimizes the learning of compact yet sufficient representations that preserve essential information for target behavior prediction while eliminating task-irrelevant redundancies. To further mitigate interaction noise, we introduce a Graph Refinement Encoder (GRE) that dynamically prunes redundant edges through learnable edge dropout mechanisms. We conduct comprehensive experiments on three real-world public datasets, which demonstrate the superior effectiveness of our framework. Beyond these widely used datasets in the academic community, we further expand our evaluation on several real industrial scenarios and conduct an online A/B testing, showing again a significant improvement in multi-behavior recommendations. The source code of our proposed HGIB is available at https://github.com/zhy99426/HGIB. △ Less

Submitted 21 July, 2025; originally announced July 2025.

Comments: Accepted by RecSys2025

Sharp estimates of quantum covering problems via a novel trace inequality

Authors: Hao-Chung Cheng, Li Gao, Christoph Hirche, Hao-Wei Huang, Po-Chieh Liu

Abstract: In this paper, we prove a novel trace inequality involving two operators. As applications, we sharpen the one-shot achievability bound on the relative entropy error in a wealth of quantum covering-type problems, such as soft covering, privacy amplification, convex splitting, quantum information decoupling, and quantum channel simulation by removing some dimension-dependent factors. Moreover, the e… ▽ More In this paper, we prove a novel trace inequality involving two operators. As applications, we sharpen the one-shot achievability bound on the relative entropy error in a wealth of quantum covering-type problems, such as soft covering, privacy amplification, convex splitting, quantum information decoupling, and quantum channel simulation by removing some dimension-dependent factors. Moreover, the established one-shot bounds extend to infinite-dimensional separable Hilbert spaces as well. The proof techniques are based on the recently developed operator layer cake theorem and an operator change-of-variable argument, which are of independent interest. △ Less

Submitted 10 July, 2025; originally announced July 2025.

SAS: Simulated Attention Score

Authors: Chuanyang Zheng, Jiankai Sun, Yihang Gao, Yuehao Wang, Peihao Wang, Jing Xiong, Liliang Ren, Hao Cheng, Janardhan Kulkarni, Yelong Shen, Atlas Wang, Mac Schwager, Anderson Schneider, Xiaodong Liu, Jianfeng Gao

Abstract: The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA), multi-query attention, group-query attention and so on. We further analyze the MHA and observe that its performance improves as the number of attention heads increases, provided the hidden size per head remains sufficien… ▽ More The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA), multi-query attention, group-query attention and so on. We further analyze the MHA and observe that its performance improves as the number of attention heads increases, provided the hidden size per head remains sufficiently large. Therefore, increasing both the head count and hidden size per head with minimal parameter overhead can lead to significant performance gains at a low cost. Motivated by this insight, we introduce Simulated Attention Score (SAS), which maintains a compact model size while simulating a larger number of attention heads and hidden feature dimension per head. This is achieved by projecting a low-dimensional head representation into a higher-dimensional space, effectively increasing attention capacity without increasing parameter count. Beyond the head representations, we further extend the simulation approach to feature dimension of the key and query embeddings, enhancing expressiveness by mimicking the behavior of a larger model while preserving the original model size. To control the parameter cost, we also propose Parameter-Efficient Attention Aggregation (PEAA). Comprehensive experiments on a variety of datasets and tasks demonstrate the effectiveness of the proposed SAS method, achieving significant improvements over different attention variants. △ Less

Submitted 10 July, 2025; originally announced July 2025.

Comments: Tech Report

Shuffling for Semantic Secrecy

Authors: Fupei Chen, Liyao Xiang, Haoxiang Sun, Hei Victor Cheng, Kaiming Shen

Abstract: Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the conventional secure coding scheme to strike a desirable tradeoff between transmission rate and leakage rate. To be more specific, for a wiretap channel, we seek to maxi… ▽ More Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the conventional secure coding scheme to strike a desirable tradeoff between transmission rate and leakage rate. To be more specific, for a wiretap channel, we seek to maximize the transmission rate while minimizing the semantic error probability under the given leakage rate constraint. Toward this end, we devise a novel semantic security communication system wherein the random shuffling pattern plays the role of the shared secret key. Intuitively, the permutation of feature sequences via shuffling would distort the semantic essence of the target data to a sufficient extent so that eavesdroppers cannot access it anymore. The proposed random shuffling method also exhibits its flexibility in working for the existing semantic communication system as a plugin. Simulations demonstrate the significant advantage of the proposed method over the benchmark in boosting secure transmission, especially when channels are prone to strong noise and unpredictable fading. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Journal ref: IEEE Transactions on Information Forensics and Security, vol. 20, pp. 5240-5255, 2025

Layer Cake Representations for Quantum Divergences

Authors: Po-Chieh Liu, Christoph Hirche, Hao-Chung Cheng

Abstract: Defining suitable quantum extensions of classical divergences often poses a challenge due to the non-commutative nature of quantum information. In this work, we propose a new approach via what we call the layer cake representation. The resulting quantum Rényi and $f$-divergences are then proven to be equivalent to those recently defined via integral representations. Nevertheless, the approach can… ▽ More Defining suitable quantum extensions of classical divergences often poses a challenge due to the non-commutative nature of quantum information. In this work, we propose a new approach via what we call the layer cake representation. The resulting quantum Rényi and $f$-divergences are then proven to be equivalent to those recently defined via integral representations. Nevertheless, the approach can provide several insights. We give an alternative proof of the integral representation of the relative entropy by Frenkel and prove a conjecture regarding a trace expression for the Rényi divergence. Additionally, we give applications to error exponents in hypothesis testing, a new Riemann-Stieltjes type integral representation and a variational representation. △ Less

Submitted 10 July, 2025; v1 submitted 9 July, 2025; originally announced July 2025.

Comments: 2nd version: typo corrected

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation

Authors: Liliang Ren, Congcong Chen, Haoran Xu, Young Jin Kim, Adam Atkinson, Zheng Zhan, Jiankai Sun, Baolin Peng, Liyuan Liu, Shuohang Wang, Hao Cheng, Jianfeng Gao, Weizhu Chen, Yelong Shen

Abstract: Recent advances in language modeling have demonstrated the effectiveness of State Space Models (SSMs) for efficient sequence modeling. While hybrid architectures such as Samba and the decoder-decoder architecture, YOCO, have shown promising performance gains over Transformers, prior works have not investigated the efficiency potential of representation sharing between SSM layers. In this paper, we… ▽ More Recent advances in language modeling have demonstrated the effectiveness of State Space Models (SSMs) for efficient sequence modeling. While hybrid architectures such as Samba and the decoder-decoder architecture, YOCO, have shown promising performance gains over Transformers, prior works have not investigated the efficiency potential of representation sharing between SSM layers. In this paper, we introduce the Gated Memory Unit (GMU), a simple yet effective mechanism for efficient memory sharing across layers. We apply it to create SambaY, a decoder-hybrid-decoder architecture that incorporates GMUs in the cross-decoder to share memory readout states from a Samba-based self-decoder. SambaY significantly enhances decoding efficiency, preserves linear pre-filling time complexity, and boosts long-context performance, all while eliminating the need for explicit positional encoding. Through extensive scaling experiments, we demonstrate that our model exhibits a significantly lower irreducible loss compared to a strong YOCO baseline, indicating superior performance scalability under large-scale compute regimes. Our largest model enhanced with Differential Attention, Phi4-mini-Flash-Reasoning, achieves significantly better performance than Phi4-mini-Reasoning on reasoning tasks such as Math500, AIME24/25, and GPQA Diamond without any reinforcement learning, while delivering up to 10x higher decoding throughput on 2K-length prompts with 32K generation length under the vLLM inference framework. We release our training codebase on open-source data at https://github.com/microsoft/ArchScale. △ Less

Submitted 16 July, 2025; v1 submitted 9 July, 2025; originally announced July 2025.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3284 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 22 July, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

Error Exponents for Quantum Packing Problems via An Operator Layer Cake Theorem

Authors: Hao-Chung Cheng, Po-Chieh Liu

Abstract: In this work, we prove a one-shot random coding bound for classical-quantum channel coding, a problem conjectured by Burnashev and Holevo in 1998. By choosing the optimal input distribution, we recover the optimal error exponent (i.e., the reliability function) of classical-quantum channels for rates above the critical rate. Our result extends to various quantum packing-type problems, including cl… ▽ More In this work, we prove a one-shot random coding bound for classical-quantum channel coding, a problem conjectured by Burnashev and Holevo in 1998. By choosing the optimal input distribution, we recover the optimal error exponent (i.e., the reliability function) of classical-quantum channels for rates above the critical rate. Our result extends to various quantum packing-type problems, including classical communication over any fully quantum channel with or without entanglement-assistance, constant composition codes, and classical data compression with quantum side information via fixed-length or variable-length coding. Our technical ingredient is to establish an operator layer cake theorem - the directional derivative of an operator logarithm admits an integral representation of certain projections. This shows that a kind of pretty-good measurement is equivalent to a randomized Holevo-Helstrom measurement, which provides an operational explanation of why the pretty-good measurement is pretty good. △ Less

Submitted 8 July, 2025; originally announced July 2025.

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

Authors: Xiangru Tang, Tianrui Qin, Tianhao Peng, Ziyang Zhou, Daniel Shao, Tingting Du, Xinming Wei, Peng Xia, Fang Wu, He Zhu, Ge Zhang, Jiaheng Liu, Xingyao Wang, Sirui Hong, Chenglin Wu, Hao Cheng, Chi Wang, Wangchunshu Zhou

Abstract: Current AI agents cannot effectively learn from each other's problem-solving experiences or use past successes to guide self-reflection and error correction in new tasks. We introduce Agent KB, a shared knowledge base that captures both high-level problem-solving strategies and detailed execution lessons, enabling knowledge transfer across agent frameworks. Agent KB implements a novel teacher-stud… ▽ More Current AI agents cannot effectively learn from each other's problem-solving experiences or use past successes to guide self-reflection and error correction in new tasks. We introduce Agent KB, a shared knowledge base that captures both high-level problem-solving strategies and detailed execution lessons, enabling knowledge transfer across agent frameworks. Agent KB implements a novel teacher-student dual-phase retrieval mechanism where student agents retrieve workflow-level patterns for strategic guidance while teacher agents identify execution-level patterns for refinement. This hierarchical approach enables agents to break out of limited reasoning pathways by incorporating diverse strategies from external sources. Evaluations on the GAIA benchmark demonstrate substantial performance gains, with Agent KB improving success rates by up to 6.06 percentage points overall under pass@1. For SWE-bench code repair tasks, our system significantly improved resolution rates, with o3-mini achieving an 8.67 percentage point gain (23 percent to 31.67 percent) in pass@1. Our ablation studies demonstrate that the refinement module proves most critical, with its removal causing a 3.85% drop on challenging Level 3 tasks, highlighting that effective knowledge transfer necessitates both strategic guidance and execution-level refinement. △ Less

Submitted 21 July, 2025; v1 submitted 8 July, 2025; originally announced July 2025.

Rule Learning for Knowledge Graph Reasoning under Agnostic Distribution Shift

Authors: Shixuan Liu, Yue He, Yunfei Wang, Hao Zou, Haoxiang Cheng, Wenjing Yang, Peng Cui, Zhong Liu

Abstract: Logical rule learning, a prominent category of knowledge graph (KG) reasoning methods, constitutes a critical research area aimed at learning explicit rules from observed facts to infer missing knowledge. However, like all KG reasoning methods, rule learning suffers from a critical weakness-its dependence on the I.I.D. assumption. This assumption can easily be violated due to selection bias during… ▽ More Logical rule learning, a prominent category of knowledge graph (KG) reasoning methods, constitutes a critical research area aimed at learning explicit rules from observed facts to infer missing knowledge. However, like all KG reasoning methods, rule learning suffers from a critical weakness-its dependence on the I.I.D. assumption. This assumption can easily be violated due to selection bias during training or agnostic distribution shifts during testing (e.g., as in query shift scenarios), ultimately undermining model performance and reliability. To enable robust KG reasoning in wild environments, this study investigates logical rule learning in the presence of agnostic test-time distribution shifts. We formally define this challenge as out-of-distribution (OOD) KG reasoning-a previously underexplored problem, and propose the Stable Rule Learning (StableRule) framework as a solution. StableRule is an end-to-end framework that combines feature decorrelation with rule learning network, to enhance OOD generalization in KG reasoning. By leveraging feature decorrelation, StableRule mitigates the adverse effects of covariate shifts arising in OOD scenarios, improving the robustness of the rule learning network. Extensive experiments on seven benchmark KGs demonstrate the framework's superior effectiveness and stability across diverse heterogeneous environments, highlighting its practical significance for real-world applications. △ Less

Submitted 10 July, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Fair Deepfake Detectors Can Generalize

Authors: Harry Cheng, Ming-Hui Liu, Yangyang Guo, Tianyi Wang, Liqiang Nie, Mohan Kankanhalli

Abstract: Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often demonstrate that these two objectives are inherently conflicting, revealing a trade-off between them. In this paper, we, for the first time, uncover and formally define a causal relationship between fairness and generali… ▽ More Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often demonstrate that these two objectives are inherently conflicting, revealing a trade-off between them. In this paper, we, for the first time, uncover and formally define a causal relationship between fairness and generalization. Building on the back-door adjustment, we show that controlling for confounders (data distribution and model capacity) enables improved generalization via fairness interventions. Motivated by this insight, we propose Demographic Attribute-insensitive Intervention Detection (DAID), a plug-and-play framework composed of: i) Demographic-aware data rebalancing, which employs inverse-propensity weighting and subgroup-wise feature normalization to neutralize distributional biases; and ii) Demographic-agnostic feature aggregation, which uses a novel alignment loss to suppress sensitive-attribute signals. Across three cross-domain benchmarks, DAID consistently achieves superior performance in both fairness and generalization compared to several state-of-the-art detectors, validating both its theoretical foundation and practical effectiveness. △ Less

Submitted 3 July, 2025; originally announced July 2025.

Comments: 14 pages, version 1

CooT: Learning to Coordinate In-Context with Coordination Transformers

Authors: Huai-Chih Wang, Hsiang-Chun Chuang, Hsi-Chun Cheng, Dai-Jie Wu, Shao-Hua Sun

Abstract: Effective coordination among artificial agents in dynamic and uncertain environments remains a significant challenge in multi-agent systems. Existing approaches, such as self-play and population-based methods, either generalize poorly to unseen partners or require extensive training. To overcome these limitations, we propose Coordination Transformers (CooT), a novel in-context coordination framewo… ▽ More Effective coordination among artificial agents in dynamic and uncertain environments remains a significant challenge in multi-agent systems. Existing approaches, such as self-play and population-based methods, either generalize poorly to unseen partners or require extensive training. To overcome these limitations, we propose Coordination Transformers (CooT), a novel in-context coordination framework that uses recent interaction histories to adapt to unseen partners rapidly. Unlike previous approaches that primarily aim to increase the diversity of training partners, CooT explicitly focuses on adapting to new partner behaviors by predicting actions aligned with observed partner interactions. Trained on interaction trajectories collected from diverse pairs of agents with complementary behaviors, CooT quickly learns effective coordination strategies without explicit supervision or fine-tuning. Evaluations on the Overcooked benchmark demonstrate that CooT significantly outperforms baseline methods in coordination tasks involving previously unseen partners. Human evaluations further confirm CooT as the most effective collaborative partner, while extensive ablations highlight its robustness, flexibility, and sensitivity to context in multi-agent scenarios. △ Less

Submitted 30 June, 2025; originally announced June 2025.

Comments: 23 pages, 10 tables, 8 figures

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers

Authors: Tzu-Quan Lin, Hsi-Chun Cheng, Hung-yi Lee, Hao Tang

Abstract: In recent years, the impact of self-supervised speech Transformers has extended to speaker-related applications. However, little research has explored how these models encode speaker information. In this work, we address this gap by identifying neurons in the feed-forward layers that are correlated with speaker information. Specifically, we analyze neurons associated with k-means clusters of self-… ▽ More In recent years, the impact of self-supervised speech Transformers has extended to speaker-related applications. However, little research has explored how these models encode speaker information. In this work, we address this gap by identifying neurons in the feed-forward layers that are correlated with speaker information. Specifically, we analyze neurons associated with k-means clusters of self-supervised features and i-vectors. Our analysis reveals that these clusters correspond to broad phonetic and gender classes, making them suitable for identifying neurons that represent speakers. By protecting these neurons during pruning, we can significantly preserve performance on speaker-related task, demonstrating their crucial role in encoding speaker information. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Low-Cost Infrastructure-Free 3D Relative Localization with Sub-Meter Accuracy in Near Field

Authors: Qiangsheng Gao, Ka Ho Cheng, Li Qiu, Zijun Gong

Abstract: Relative localization in the near-field scenario is critically important for unmanned vehicle (UxV) applications. Although related works addressing 2D relative localization problem have been widely studied for unmanned ground vehicles (UGVs), the problem in 3D scenarios for unmanned aerial vehicles (UAVs) involves more uncertainties and remains to be investigated. Inspired by the phenomenon that a… ▽ More Relative localization in the near-field scenario is critically important for unmanned vehicle (UxV) applications. Although related works addressing 2D relative localization problem have been widely studied for unmanned ground vehicles (UGVs), the problem in 3D scenarios for unmanned aerial vehicles (UAVs) involves more uncertainties and remains to be investigated. Inspired by the phenomenon that animals can achieve swarm behaviors solely based on individual perception of relative information, this study proposes an infrastructure-free 3D relative localization framework that relies exclusively on onboard ultra-wideband (UWB) sensors. Leveraging 2D relative positioning research, we conducted feasibility analysis, system modeling, simulations, performance evaluation, and field tests using UWB sensors. The key contributions of this work include: derivation of the Cramér-Rao lower bound (CRLB) and geometric dilution of precision (GDOP) for near-field scenarios; development of two localization algorithms -- one based on Euclidean distance matrix (EDM) and another employing maximum likelihood estimation (MLE); comprehensive performance comparison and computational complexity analysis against state-of-the-art methods; simulation studies and field experiments; a novel sensor deployment strategy inspired by animal behavior, enabling single-sensor implementation within the proposed framework for UxV applications. The theoretical, simulation, and experimental results demonstrate strong generalizability to other 3D near-field localization tasks, with significant potential for a cost-effective cross-platform UxV collaborative system. △ Less

Submitted 23 June, 2025; originally announced June 2025.

MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners

Authors: Fang-Duo Tsai, Shih-Lun Wu, Weijaw Lee, Sheng-Ping Yang, Bo-Rui Chen, Hao-Chung Cheng, Yi-Hsuan Yang

Abstract: We propose MuseControlLite, a lightweight mechanism designed to fine-tune text-to-music generation models for precise conditioning using various time-varying musical attributes and reference audio signals. The key finding is that positional embeddings, which have been seldom used by text-to-music generation models in the conditioner for text conditions, are critical when the condition of interest… ▽ More We propose MuseControlLite, a lightweight mechanism designed to fine-tune text-to-music generation models for precise conditioning using various time-varying musical attributes and reference audio signals. The key finding is that positional embeddings, which have been seldom used by text-to-music generation models in the conditioner for text conditions, are critical when the condition of interest is a function of time. Using melody control as an example, our experiments show that simply adding rotary positional embeddings to the decoupled cross-attention layers increases control accuracy from 56.6% to 61.1%, while requiring 6.75 times fewer trainable parameters than state-of-the-art fine-tuning mechanisms, using the same pre-trained diffusion Transformer model of Stable Audio Open. We evaluate various forms of musical attribute control, audio inpainting, and audio outpainting, demonstrating improved controllability over MusicGen-Large and Stable Audio Open ControlNet at a significantly lower fine-tuning cost, with only 85M trainble parameters. Source code, model checkpoints, and demo examples are available at: https://musecontrollite.github.io/web/. △ Less

Submitted 24 June, 2025; v1 submitted 23 June, 2025; originally announced June 2025.

Comments: Accepted by the 42nd International Conference on Machine Learning (ICML 2025)

Reflective VLM Planning for Dual-Arm Desktop Cleaning: Bridging Open-Vocabulary Perception and Precise Manipulation

Authors: Yufan Liu, Yi Wu, Gweneth Ge, Haoliang Cheng, Rui Liu

Abstract: Desktop cleaning demands open-vocabulary recognition and precise manipulation for heterogeneous debris. We propose a hierarchical framework integrating reflective Vision-Language Model (VLM) planning with dual-arm execution via structured scene representation. Grounded-SAM2 facilitates open-vocabulary detection, while a memory-augmented VLM generates, critiques, and revises manipulation sequences.… ▽ More Desktop cleaning demands open-vocabulary recognition and precise manipulation for heterogeneous debris. We propose a hierarchical framework integrating reflective Vision-Language Model (VLM) planning with dual-arm execution via structured scene representation. Grounded-SAM2 facilitates open-vocabulary detection, while a memory-augmented VLM generates, critiques, and revises manipulation sequences. These sequences are converted into parametric trajectories for five primitives executed by coordinated Franka arms. Evaluated in simulated scenarios, our system achieving 87.2% task completion, a 28.8% improvement over static VLM and 36.2% over single-arm baselines. Structured memory integration proves crucial for robust, generalizable manipulation while maintaining real-time control performance. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Noise-Informed Diffusion-Generated Image Detection with Anomaly Attention

Authors: Weinan Guan, Wei Wang, Bo Peng, Ziwen He, Jing Dong, Haonan Cheng

Abstract: With the rapid development of image generation technologies, especially the advancement of Diffusion Models, the quality of synthesized images has significantly improved, raising concerns among researchers about information security. To mitigate the malicious abuse of diffusion models, diffusion-generated image detection has proven to be an effective countermeasure.However, a key challenge for for… ▽ More With the rapid development of image generation technologies, especially the advancement of Diffusion Models, the quality of synthesized images has significantly improved, raising concerns among researchers about information security. To mitigate the malicious abuse of diffusion models, diffusion-generated image detection has proven to be an effective countermeasure.However, a key challenge for forgery detection is generalising to diffusion models not seen during training. In this paper, we address this problem by focusing on image noise. We observe that images from different diffusion models share similar noise patterns, distinct from genuine images. Building upon this insight, we introduce a novel Noise-Aware Self-Attention (NASA) module that focuses on noise regions to capture anomalous patterns. To implement a SOTA detection model, we incorporate NASA into Swin Transformer, forming an novel detection architecture NASA-Swin. Additionally, we employ a cross-modality fusion embedding to combine RGB and noise images, along with a channel mask strategy to enhance feature learning from both modalities. Extensive experiments demonstrate the effectiveness of our approach in enhancing detection capabilities for diffusion-generated images. When encountering unseen generation methods, our approach achieves the state-of-the-art performance.Our code is available at https://github.com/WeinanGuan/NASA-Swin. △ Less

Submitted 20 June, 2025; originally announced June 2025.

Comments: Accepted by TIFS 2025. Our code is availabel at https://github.com/WeinanGuan/NASA-Swin

Journal ref: IEEE Trans. Inf. Forensics Security, vol.20, pp. 5256-5268, 2025

OneRec Technical Report

Authors: Guorui Zhou, Jiaxin Deng, Jinghao Zhang, Kuo Cai, Lejian Ren, Qiang Luo, Qianqian Wang, Qigen Hu, Rui Huang, Shiyao Wang, Weifeng Ding, Wuchao Li, Xinchen Luo, Xingmei Wang, Zexuan Cheng, Zixing Zhang, Bin Zhang, Boxuan Wang, Chaoyi Ma, Chengru Song, Chenhui Wang, Di Wang, Dongxue Meng, Fan Yang, Fangyu Zhang , et al. (40 additional authors not shown)

Abstract: Recommender systems have been widely used in various large-scale user-oriented platforms for many years. However, compared to the rapid developments in the AI community, recommendation systems have not achieved a breakthrough in recent years. For instance, they still rely on a multi-stage cascaded architecture rather than an end-to-end approach, leading to computational fragmentation and optimizat… ▽ More Recommender systems have been widely used in various large-scale user-oriented platforms for many years. However, compared to the rapid developments in the AI community, recommendation systems have not achieved a breakthrough in recent years. For instance, they still rely on a multi-stage cascaded architecture rather than an end-to-end approach, leading to computational fragmentation and optimization inconsistencies, and hindering the effective application of key breakthrough technologies from the AI community in recommendation scenarios. To address these issues, we propose OneRec, which reshapes the recommendation system through an end-to-end generative approach and achieves promising results. Firstly, we have enhanced the computational FLOPs of the current recommendation model by 10 $\times$ and have identified the scaling laws for recommendations within certain boundaries. Secondly, reinforcement learning techniques, previously difficult to apply for optimizing recommendations, show significant potential in this framework. Lastly, through infrastructure optimizations, we have achieved 23.7% and 28.8% Model FLOPs Utilization (MFU) on flagship GPUs during training and inference, respectively, aligning closely with the LLM community. This architecture significantly reduces communication and storage overhead, resulting in operating expense that is only 10.6% of traditional recommendation pipelines. Deployed in Kuaishou/Kuaishou Lite APP, it handles 25% of total queries per second, enhancing overall App Stay Time by 0.54% and 1.24%, respectively. Additionally, we have observed significant increases in metrics such as 7-day Lifetime, which is a crucial indicator of recommendation experience. We also provide practical lessons and insights derived from developing, optimizing, and maintaining a production-scale recommendation system with significant real-world impact. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Comments: Authors are listed alphabetically by their first name

An Exploration of Mamba for Speech Self-Supervised Models

Authors: Tzu-Quan Lin, Heng-Cheng Kuo, Tzu-Chieh Wei, Hsi-Chun Cheng, Chun-Wei Chen, Hsien-Fu Hsiao, Yu Tsao, Hung-yi Lee

Abstract: While Mamba has demonstrated strong performance in language modeling, its potential as a speech self-supervised (SSL) model remains underexplored, with prior studies limited to isolated tasks. To address this, we explore Mamba-based HuBERT models as alternatives to Transformer-based SSL architectures. Leveraging the linear-time Selective State Space, these models enable fine-tuning on long-context… ▽ More While Mamba has demonstrated strong performance in language modeling, its potential as a speech self-supervised (SSL) model remains underexplored, with prior studies limited to isolated tasks. To address this, we explore Mamba-based HuBERT models as alternatives to Transformer-based SSL architectures. Leveraging the linear-time Selective State Space, these models enable fine-tuning on long-context ASR with significantly lower compute. Moreover, they show superior performance when fine-tuned for streaming ASR. Beyond fine-tuning, these models show competitive performance on SUPERB probing benchmarks, particularly in causal settings. Our analysis shows that they yield higher-quality quantized representations and capture speaker-related features more distinctly than Transformer-based models. These findings highlight Mamba-based SSL as a promising and complementary direction for long-sequence modeling, real-time speech modeling, and speech unit extraction. △ Less

Submitted 14 June, 2025; originally announced June 2025.

A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data

Authors: Cheng-Kang Chou, Chan-Jan Hsu, Ho-Lam Chung, Liang-Hsuan Tseng, Hsi-Chun Cheng, Yu-Kuan Fu, Kuan Po Huang, Hung-Yi Lee

Abstract: We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train a high-fidelity text-to-speech (TTS) system. Then, synthesized speech text pairs are bootstrapped into the original ASR system, completing the closed-loop self-improvement cycle. W… ▽ More We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train a high-fidelity text-to-speech (TTS) system. Then, synthesized speech text pairs are bootstrapped into the original ASR system, completing the closed-loop self-improvement cycle. We demonstrated the effectiveness of the framework on Taiwanese Mandarin speech. Leveraging 6,000 hours of unlabeled speech, a moderate amount of text data, and synthetic content from the AI models, we adapt Whisper-large-v2 into a specialized model, Twister. Twister reduces error rates by up to 20% on Mandarin and 50% on Mandarin-English code-switching benchmarks compared to Whisper. Results highlight the framework as a compelling alternative to pseudo-labeling self-distillation approaches and provides a practical pathway for improving ASR performance in low-resource or domain-specific settings. △ Less

Submitted 16 June, 2025; v1 submitted 10 June, 2025; originally announced June 2025.

RoCA: Robust Cross-Domain End-to-End Autonomous Driving

Authors: Rajeev Yasarla, Shizhong Han, Hsin-Pai Cheng, Litian Liu, Shweta Mahajan, Apratim Bhattacharyya, Yunxiao Shi, Risheek Garrepalli, Hong Cai, Fatih Porikli

Abstract: End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deployment across domains (e.g., cities). Although several works have incorporated Large Language Models (LLMs) to leverage their open-world knowledge, LLMs do not guarantee cross-domain driving performance and may incur prohib… ▽ More End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deployment across domains (e.g., cities). Although several works have incorporated Large Language Models (LLMs) to leverage their open-world knowledge, LLMs do not guarantee cross-domain driving performance and may incur prohibitive retraining costs during domain adaptation. In this paper, we propose RoCA, a novel framework for robust cross-domain E2E autonomous driving. RoCA formulates the joint probabilistic distribution over the tokens that encode ego and surrounding vehicle information in the E2E pipeline. Instantiating with a Gaussian process (GP), RoCA learns a set of basis tokens with corresponding trajectories, which span diverse driving scenarios. Then, given any driving scene, it is able to probabilistically infer the future trajectory. By using RoCA together with a base E2E model in source-domain training, we improve the generalizability of the base model, without requiring extra inference computation. In addition, RoCA enables robust adaptation on new target domains, significantly outperforming direct finetuning. We extensively evaluate RoCA on various cross-domain scenarios and show that it achieves strong domain generalization and adaptation performance. △ Less

Submitted 17 June, 2025; v1 submitted 11 June, 2025; originally announced June 2025.

EMG-Driven Stiffness-Modulating Palpation for Telerehabilitation

Authors: Thomas M. Kwok, Hilary HY Cheng, Wai Tuck Chow

Abstract: In this work, we introduce HJ-Pal, a lightweight wearable haptic device that leverages EMG-driven honeycomb jamming to render muscle activation as kinesthetic feedback, enabling remote palpation for small muscle assessment in telerehabilitation. In this work, we introduce HJ-Pal, a lightweight wearable haptic device that leverages EMG-driven honeycomb jamming to render muscle activation as kinesthetic feedback, enabling remote palpation for small muscle assessment in telerehabilitation. △ Less

Submitted 12 June, 2025; v1 submitted 9 June, 2025; originally announced June 2025.

Comments: Accepted by the Workshop on Human-Robot Contact and Manipulation (HRCM 2025) at RSS Conference 2025

FMaMIL: Frequency-Driven Mamba Multi-Instance Learning for Weakly Supervised Lesion Segmentation in Medical Images

Authors: Hangbei Cheng, Xiaorong Dong, Xueyu Liu, Jianan Zhang, Xuetao Ma, Mingqiang Wei, Liansheng Wang, Junxin Chen, Yongfei Wu

Abstract: Accurate lesion segmentation in histopathology images is essential for diagnostic interpretation and quantitative analysis, yet it remains challenging due to the limited availability of costly pixel-level annotations. To address this, we propose FMaMIL, a novel two-stage framework for weakly supervised lesion segmentation based solely on image-level labels. In the first stage, a lightweight Mamba-… ▽ More Accurate lesion segmentation in histopathology images is essential for diagnostic interpretation and quantitative analysis, yet it remains challenging due to the limited availability of costly pixel-level annotations. To address this, we propose FMaMIL, a novel two-stage framework for weakly supervised lesion segmentation based solely on image-level labels. In the first stage, a lightweight Mamba-based encoder is introduced to capture long-range dependencies across image patches under the MIL paradigm. To enhance spatial sensitivity and structural awareness, we design a learnable frequency-domain encoding module that supplements spatial-domain features with spectrum-based information. CAMs generated in this stage are used to guide segmentation training. In the second stage, we refine the initial pseudo labels via a CAM-guided soft-label supervision and a self-correction mechanism, enabling robust training even under label noise. Extensive experiments on both public and private histopathology datasets demonstrate that FMaMIL outperforms state-of-the-art weakly supervised methods without relying on pixel-level annotations, validating its effectiveness and potential for digital pathology applications. △ Less

Submitted 9 June, 2025; originally announced June 2025.

RAPID Hand: A Robust, Affordable, Perception-Integrated, Dexterous Manipulation Platform for Generalist Robot Autonomy

Authors: Zhaoliang Wan, Zetong Bi, Zida Zhou, Hao Ren, Yiming Zeng, Yihan Li, Lu Qi, Xu Yang, Ming-Hsuan Yang, Hui Cheng

Abstract: This paper addresses the scarcity of low-cost but high-dexterity platforms for collecting real-world multi-fingered robot manipulation data towards generalist robot autonomy. To achieve it, we propose the RAPID Hand, a co-optimized hardware and software platform where the compact 20-DoF hand, robust whole-hand perception, and high-DoF teleoperation interface are jointly designed. Specifically, RAP… ▽ More This paper addresses the scarcity of low-cost but high-dexterity platforms for collecting real-world multi-fingered robot manipulation data towards generalist robot autonomy. To achieve it, we propose the RAPID Hand, a co-optimized hardware and software platform where the compact 20-DoF hand, robust whole-hand perception, and high-DoF teleoperation interface are jointly designed. Specifically, RAPID Hand adopts a compact and practical hand ontology and a hardware-level perception framework that stably integrates wrist-mounted vision, fingertip tactile sensing, and proprioception with sub-7 ms latency and spatial alignment. Collecting high-quality demonstrations on high-DoF hands is challenging, as existing teleoperation methods struggle with precision and stability on complex multi-fingered systems. We address this by co-optimizing hand design, perception integration, and teleoperation interface through a universal actuation scheme, custom perception electronics, and two retargeting constraints. We evaluate the platform's hardware, perception, and teleoperation interface. Training a diffusion policy on collected data shows superior performance over prior works, validating the system's capability for reliable, high-quality data collection. The platform is constructed from low-cost and off-the-shelf components and will be made public to ensure reproducibility and ease of adoption. △ Less

Submitted 9 June, 2025; originally announced June 2025.

FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices

Authors: Shizhong Han, Hsin-Pai Cheng, Hong Cai, Jihad Masri, Soyeb Nagori, Fatih Porikli

Abstract: Existing LiDAR 3D object detection methods predominantely rely on sparse convolutions and/or transformers, which can be challenging to run on resource-constrained edge devices, due to irregular memory access patterns and high computational costs. In this paper, we propose FALO, a hardware-friendly approach to LiDAR 3D detection, which offers both state-of-the-art (SOTA) detection accuracy and fast… ▽ More Existing LiDAR 3D object detection methods predominantely rely on sparse convolutions and/or transformers, which can be challenging to run on resource-constrained edge devices, due to irregular memory access patterns and high computational costs. In this paper, we propose FALO, a hardware-friendly approach to LiDAR 3D detection, which offers both state-of-the-art (SOTA) detection accuracy and fast inference speed. More specifically, given the 3D point cloud and after voxelization, FALO first arranges sparse 3D voxels into a 1D sequence based on their coordinates and proximity. The sequence is then processed by our proposed ConvDotMix blocks, consisting of large-kernel convolutions, Hadamard products, and linear layers. ConvDotMix provides sufficient mixing capability in both spatial and embedding dimensions, and introduces higher-order nonlinear interaction among spatial features. Furthermore, when going through the ConvDotMix layers, we introduce implicit grouping, which balances the tensor dimensions for more efficient inference and takes into account the growing receptive field. All these operations are friendly to run on resource-constrained platforms and proposed FALO can readily deploy on compact, embedded devices. Our extensive evaluation on LiDAR 3D detection benchmarks such as nuScenes and Waymo shows that FALO achieves competitive performance. Meanwhile, FALO is 1.6~9.8x faster than the latest SOTA on mobile Graphics Processing Unit (GPU) and mobile Neural Processing Unit (NPU). △ Less

Submitted 4 June, 2025; originally announced June 2025.

A Foundation Model for Spatial Proteomics

Authors: Muhammad Shaban, Yuzhou Chang, Huaying Qiu, Yao Yu Yeo, Andrew H. Song, Guillaume Jaume, Yuchen Wang, Luca L. Weishaupt, Tong Ding, Anurag Vaidya, Abdallah Lamane, Daniel Shao, Mohammed Zidane, Yunhao Bai, Paige McCallum, Shuli Luo, Wenrui Wu, Yang Wang, Precious Cramer, Chi Ngai Chan, Pierre Stephan, Johanna Schaffenrath, Jia Le Lee, Hendrik A. Michel, Caiwei Tian , et al. (35 additional authors not shown)

Abstract: Foundation models have begun to transform image analysis by acting as pretrained generalist backbones that can be adapted to many tasks even when post-training data are limited, yet their impact on spatial proteomics, imaging that maps proteins at single-cell resolution, remains limited. Here, we introduce KRONOS, a foundation model built for spatial proteomics. KRONOS was trained in a self-superv… ▽ More Foundation models have begun to transform image analysis by acting as pretrained generalist backbones that can be adapted to many tasks even when post-training data are limited, yet their impact on spatial proteomics, imaging that maps proteins at single-cell resolution, remains limited. Here, we introduce KRONOS, a foundation model built for spatial proteomics. KRONOS was trained in a self-supervised manner on over 47 million image patches covering 175 protein markers, 16 tissue types, and 8 fluorescence-based imaging platforms. We introduce key architectural adaptations to address the high-dimensional, multi-channel, and heterogeneous nature of multiplex imaging. We demonstrate that KRONOS learns biologically meaningful representations across multiple scales, ranging from cellular and microenvironment to tissue levels, enabling it to address diverse downstream tasks, including cell phenotyping, region classification, and patient stratification. Evaluated across 11 independent cohorts, KRONOS achieves state-of-the-art performance across cell phenotyping, treatment response prediction, and retrieval tasks, and is highly data-efficient. KRONOS also introduces the paradigm of segmentation-free patch-level processing for efficient and scalable spatial proteomics analysis, allowing cross-institutional comparisons, and as an image reverse search engine for spatial patterns. Together, these results position KRONOS as a flexible and scalable tool for spatial proteomics. The model is publicly accessible at https://github.com/mahmoodlab/KRONOS. △ Less

Submitted 3 June, 2025; originally announced June 2025.

NextQuill: Causal Preference Modeling for Enhancing LLM Personalization

Authors: Xiaoyan Zhao, Juntao You, Yang Zhang, Wenjie Wang, Hong Cheng, Fuli Feng, See-Kiong Ng, Tat-Seng Chua

Abstract: Personalizing large language models (LLMs) for individual users has become increasingly important as they are progressively integrated into real-world applications to support users' daily lives. However, existing personalization approaches often fail to distinguish which components of model predictions and training data truly reflect user preferences, leading to superficial personalization alignme… ▽ More Personalizing large language models (LLMs) for individual users has become increasingly important as they are progressively integrated into real-world applications to support users' daily lives. However, existing personalization approaches often fail to distinguish which components of model predictions and training data truly reflect user preferences, leading to superficial personalization alignment. In this paper, we introduce NextQuill, a novel LLM personalization alignment framework grounded in causal preference modeling. We approach personalization from a causal perspective, treating both model predictions and ground-truth data generation as outcomes influenced by user preferences, along with other factors. We define the true preference effect as the causal impact of user history (which reflects preferences) on each token prediction or data generation instance, estimated through causal intervention techniques. Building on this insight, NextQuill introduces two complementary alignment strategies: (1) aligning model-internal causal preference effects on predictions with those reflected in ground-truth data, rather than indiscriminately fitting predictions, and (2) focusing on fitting preference-bearing tokens identified via ground-truth data preference effects, rather than treating all tokens uniformly. By integrating these strategies, NextQuill shifts the alignment process toward learning from causal preference effects, facilitating more effective and personalized adaptation. Experiments across multiple personalization benchmarks demonstrate that NextQuill significantly improves personalization quality, offering a principled, causal foundation for LLM personalization. Our codes are available on https://github.com/juntaoyou/NextQuill. △ Less

Submitted 2 June, 2025; originally announced June 2025.

RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report

Authors: Marcos V. Conde, Radu Timofte, Radu Berdan, Beril Besbinar, Daisuke Iso, Pengzhou Ji, Xiong Dun, Zeying Fan, Chen Wu, Zhansheng Wang, Pengbo Zhang, Jiazi Huang, Qinglin Liu, Wei Yu, Shengping Zhang, Xiangyang Ji, Kyungsik Kim, Minkyung Kim, Hwalmin Lee, Hekun Ma, Huan Zheng, Yanyan Wei, Zhao Zhang, Jing Fang, Meilin Gao , et al. (8 additional authors not shown)

Abstract: Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public sRGB datasets. For this reason, many approaches try to generate realistic RAW images using sensor information and sRGB images. This paper covers the second challenge on RAW… ▽ More Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public sRGB datasets. For this reason, many approaches try to generate realistic RAW images using sensor information and sRGB images. This paper covers the second challenge on RAW Reconstruction from sRGB (Reverse ISP). We aim to recover RAW sensor images from smartphones given the corresponding sRGB images without metadata and, by doing this, ``reverse" the ISP transformation. Over 150 participants joined this NTIRE 2025 challenge and submitted efficient models. The proposed methods and benchmark establish the state-of-the-art for generating realistic RAW data. △ Less

Submitted 2 June, 2025; originally announced June 2025.

Comments: CVPR 2025 - New Trends in Image Restoration and Enhancement (NTIRE)

Many-for-Many: Unify the Training of Multiple Video and Image Generation and Manipulation Tasks

Authors: Tao Yang, Ruibin Li, Yangming Shi, Yuqi Zhang, Qide Dong, Haoran Cheng, Weiguo Feng, Shilei Wen, Bingyue Peng, Lei Zhang

Abstract: Diffusion models have shown impressive performance in many visual generation and manipulation tasks. Many existing methods focus on training a model for a specific task, especially, text-to-video (T2V) generation, while many other works focus on finetuning the pretrained T2V model for image-to-video (I2V), video-to-video (V2V), image and video manipulation tasks, etc. However, training a strong T2… ▽ More Diffusion models have shown impressive performance in many visual generation and manipulation tasks. Many existing methods focus on training a model for a specific task, especially, text-to-video (T2V) generation, while many other works focus on finetuning the pretrained T2V model for image-to-video (I2V), video-to-video (V2V), image and video manipulation tasks, etc. However, training a strong T2V foundation model requires a large amount of high-quality annotations, which is very costly. In addition, many existing models can perform only one or several tasks. In this work, we introduce a unified framework, namely many-for-many, which leverages the available training data from many different visual generation and manipulation tasks to train a single model for those different tasks. Specifically, we design a lightweight adapter to unify the different conditions in different tasks, then employ a joint image-video learning strategy to progressively train the model from scratch. Our joint learning leads to a unified visual generation and manipulation model with improved video generation performance. In addition, we introduce depth maps as a condition to help our model better perceive the 3D space in visual generation. Two versions of our model are trained with different model sizes (8B and 2B), each of which can perform more than 10 different tasks. In particular, our 8B model demonstrates highly competitive performance in video generation tasks compared to open-source and even commercial engines. Our models and source codes are available at https://github.com/leeruibin/MfM.git. △ Less

Submitted 12 July, 2025; v1 submitted 2 June, 2025; originally announced June 2025.

FDSG: Forecasting Dynamic Scene Graphs

Authors: Yi Yang, Yuren Cong, Hao Cheng, Bodo Rosenhahn, Michael Ying Yang

Abstract: Dynamic scene graph generation extends scene graph generation from images to videos by modeling entity relationships and their temporal evolution. However, existing methods either generate scene graphs from observed frames without explicitly modeling temporal dynamics, or predict only relationships while assuming static entity labels and locations. These limitations hinder effective extrapolation… ▽ More Dynamic scene graph generation extends scene graph generation from images to videos by modeling entity relationships and their temporal evolution. However, existing methods either generate scene graphs from observed frames without explicitly modeling temporal dynamics, or predict only relationships while assuming static entity labels and locations. These limitations hinder effective extrapolation of both entity and relationship dynamics, restricting video scene understanding. We propose Forecasting Dynamic Scene Graphs (FDSG), a novel framework that predicts future entity labels, bounding boxes, and relationships, for unobserved frames, while also generating scene graphs for observed frames. Our scene graph forecast module leverages query decomposition and neural stochastic differential equations to model entity and relationship dynamics. A temporal aggregation module further refines predictions by integrating forecasted and observed information via cross-attention. To benchmark FDSG, we introduce Scene Graph Forecasting, a new task for full future scene graph prediction. Experiments on Action Genome show that FDSG outperforms state-of-the-art methods on dynamic scene graph generation, scene graph anticipation, and scene graph forecasting. Codes will be released upon publication. △ Less

Submitted 18 July, 2025; v1 submitted 2 June, 2025; originally announced June 2025.

Comments: 16 pages, 8 figures, 12 tables

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents

Authors: Xiao Yu, Baolin Peng, Ruize Xu, Michel Galley, Hao Cheng, Suman Nath, Jianfeng Gao, Zhou Yu

Abstract: Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal decomposition, and self-reflection. However, it is unclear what behavior is effective and what behavior is missing for long-horizon AI agents tasks. In this work, we pro… ▽ More Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal decomposition, and self-reflection. However, it is unclear what behavior is effective and what behavior is missing for long-horizon AI agents tasks. In this work, we propose Dyna-Think, a thinking framework that integrates planning with an internal world model with reasoning and acting to enhance AI agent performance. To enable Dyna-Think, we propose Dyna-Think Imitation Learning (DIT) and Dyna-Think Dyna Training (DDT). To initialize a policy with Dyna-Think, DIT reconstructs the thinking process of R1 to focus on performing world model simulation relevant to the proposed (and planned) action, and trains the policy using this reconstructed data. To enhance Dyna-Think, DDT uses a two-stage training process to first improve the agent's world modeling ability via objectives such as state prediction or critique generation, and then improve the agent's action via policy training. We evaluate our methods on OSWorld, and demonstrate that Dyna-Think improves the agent's in-domain and out-of-domain performance, achieving similar best-of-n performance compared to R1 while generating 2x less tokens on average. Our extensive empirical studies reveal that 1) using critique generation for world model training is effective to improve policy performance; and 2) AI agents with better performance correlate with better world modeling abilities. We believe our results suggest a promising research direction to integrate world model simulation into AI agents to enhance their reasoning, planning, and acting capabilities. △ Less

Submitted 30 May, 2025; originally announced June 2025.

DSAGL: Dual-Stream Attention-Guided Learning for Weakly Supervised Whole Slide Image Classification

Authors: Daoxi Cao, Hangbei Cheng, Yijin Li, Ruolin Zhou, Xuehan Zhang, Xinyi Li, Binwei Li, Xuancheng Gu, Jianan Zhang, Xueyu Liu, Yongfei Wu

Abstract: Whole-slide images (WSIs) are critical for cancer diagnosis due to their ultra-high resolution and rich semantic content. However, their massive size and the limited availability of fine-grained annotations pose substantial challenges for conventional supervised learning. We propose DSAGL (Dual-Stream Attention-Guided Learning), a novel weakly supervised classification framework that combines a te… ▽ More Whole-slide images (WSIs) are critical for cancer diagnosis due to their ultra-high resolution and rich semantic content. However, their massive size and the limited availability of fine-grained annotations pose substantial challenges for conventional supervised learning. We propose DSAGL (Dual-Stream Attention-Guided Learning), a novel weakly supervised classification framework that combines a teacher-student architecture with a dual-stream design. DSAGL explicitly addresses instance-level ambiguity and bag-level semantic consistency by generating multi-scale attention-based pseudo labels and guiding instance-level learning. A shared lightweight encoder (VSSMamba) enables efficient long-range dependency modeling, while a fusion-attentive module (FASA) enhances focus on sparse but diagnostically relevant regions. We further introduce a hybrid loss to enforce mutual consistency between the two streams. Experiments on CIFAR-10, NCT-CRC, and TCGA-Lung datasets demonstrate that DSAGL consistently outperforms state-of-the-art MIL baselines, achieving superior discriminative performance and robustness under weak supervision. △ Less

Submitted 27 June, 2025; v1 submitted 29 May, 2025; originally announced May 2025.

GET: Goal-directed Exploration and Targeting for Large-Scale Unknown Environments

Authors: Lanxiang Zheng, Ruidong Mei, Mingxin Wei, Hao Ren, Hui Cheng

Abstract: Object search in large-scale, unstructured environments remains a fundamental challenge in robotics, particularly in dynamic or expansive settings such as outdoor autonomous exploration. This task requires robust spatial reasoning and the ability to leverage prior experiences. While Large Language Models (LLMs) offer strong semantic capabilities, their application in embodied contexts is limited b… ▽ More Object search in large-scale, unstructured environments remains a fundamental challenge in robotics, particularly in dynamic or expansive settings such as outdoor autonomous exploration. This task requires robust spatial reasoning and the ability to leverage prior experiences. While Large Language Models (LLMs) offer strong semantic capabilities, their application in embodied contexts is limited by a grounding gap in spatial reasoning and insufficient mechanisms for memory integration and decision consistency.To address these challenges, we propose GET (Goal-directed Exploration and Targeting), a framework that enhances object search by combining LLM-based reasoning with experience-guided exploration. At its core is DoUT (Diagram of Unified Thought), a reasoning module that facilitates real-time decision-making through a role-based feedback loop, integrating task-specific criteria and external memory. For repeated tasks, GET maintains a probabilistic task map based on a Gaussian Mixture Model, allowing for continual updates to object-location priors as environments evolve.Experiments conducted in real-world, large-scale environments demonstrate that GET improves search efficiency and robustness across multiple LLMs and task settings, significantly outperforming heuristic and LLM-only baselines. These results suggest that structured LLM integration provides a scalable and generalizable approach to embodied decision-making in complex environments. △ Less

Submitted 28 May, 2025; v1 submitted 27 May, 2025; originally announced May 2025.

Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space

Authors: Jinrong Yang, Kexun Chen, Zhuoling Li, Shengkai Wu, Yong Zhao, Liangliang Ren, Wenqiu Luo, Chaohui Shang, Meiyu Zhi, Linfeng Gao, Mingshan Sun, Hui Cheng

Abstract: Imitation learning (IL) with human demonstrations is a promising method for robotic manipulation tasks. While minimal demonstrations enable robotic action execution, achieving high success rates and generalization requires high cost, e.g., continuously adding data or incrementally conducting human-in-loop processes with complex hardware/software systems. In this paper, we rethink the state/action… ▽ More Imitation learning (IL) with human demonstrations is a promising method for robotic manipulation tasks. While minimal demonstrations enable robotic action execution, achieving high success rates and generalization requires high cost, e.g., continuously adding data or incrementally conducting human-in-loop processes with complex hardware/software systems. In this paper, we rethink the state/action space of the data collection pipeline as well as the underlying factors responsible for the prediction of non-robust actions. To this end, we introduce a Hierarchical Data Collection Space (HD-Space) for robotic imitation learning, a simple data collection scheme, endowing the model to train with proactive and high-quality data. Specifically, We segment the fine manipulation task into multiple key atomic tasks from a high-level perspective and design atomic state/action spaces for human demonstrations, aiming to generate robust IL data. We conduct empirical evaluations across two simulated and five real-world long-horizon manipulation tasks and demonstrate that IL policy training with HD-Space-based data can achieve significantly enhanced policy performance. HD-Space allows the use of a small amount of demonstration data to train a more powerful policy, particularly for long-horizon manipulation tasks. We aim for HD-Space to offer insights into optimizing data quality and guiding data scaling. project page: https://hd-space-robotics.github.io. △ Less

Submitted 22 May, 2025; originally announced May 2025.

MPL: Multiple Programming Languages with Large Language Models for Information Extraction

Authors: Bo Li, Gexiang Fang, Wei Ye, Zhenghua Xu, Jinglei Zhang, Hao Cheng, Shikun Zhang

Abstract: Recent research in information extraction (IE) focuses on utilizing code-style inputs to enhance structured output generation. The intuition behind this is that the programming languages (PLs) inherently exhibit greater structural organization than natural languages (NLs). This structural advantage makes PLs particularly suited for IE tasks. Nevertheless, existing research primarily focuses on Pyt… ▽ More Recent research in information extraction (IE) focuses on utilizing code-style inputs to enhance structured output generation. The intuition behind this is that the programming languages (PLs) inherently exhibit greater structural organization than natural languages (NLs). This structural advantage makes PLs particularly suited for IE tasks. Nevertheless, existing research primarily focuses on Python for code-style simulation, overlooking the potential of other widely-used PLs (e.g., C++ and Java) during the supervised fine-tuning (SFT) phase. In this research, we propose \textbf{M}ultiple \textbf{P}rogramming \textbf{L}anguages with large language models for information extraction (abbreviated as \textbf{MPL}), a novel framework that explores the potential of incorporating different PLs in the SFT phase. Additionally, we introduce \texttt{function-prompt} with virtual running to simulate code-style inputs more effectively and efficiently. Experimental results on a wide range of datasets demonstrate the effectiveness of MPL. Furthermore, we conduct extensive experiments to provide a comprehensive analysis. We have released our code for future research. △ Less

Submitted 21 May, 2025; originally announced May 2025.

Comments: Findings of ACL2025

Scalable Autoregressive 3D Molecule Generation

Authors: Austin H. Cheng, Chong Sun, Alán Aspuru-Guzik

Abstract: Generative models of 3D molecular structure play a rapidly growing role in the design and simulation of molecules. Diffusion models currently dominate the space of 3D molecule generation, while autoregressive models have trailed behind. In this work, we present Quetzal, a simple but scalable autoregressive model that builds molecules atom-by-atom in 3D. Treating each molecule as an ordered sequenc… ▽ More Generative models of 3D molecular structure play a rapidly growing role in the design and simulation of molecules. Diffusion models currently dominate the space of 3D molecule generation, while autoregressive models have trailed behind. In this work, we present Quetzal, a simple but scalable autoregressive model that builds molecules atom-by-atom in 3D. Treating each molecule as an ordered sequence of atoms, Quetzal combines a causal transformer that predicts the next atom's discrete type with a smaller Diffusion MLP that models the continuous next-position distribution. Compared to existing autoregressive baselines, Quetzal achieves substantial improvements in generation quality and is competitive with the performance of state-of-the-art diffusion models. In addition, by reducing the number of expensive forward passes through a dense transformer, Quetzal enables significantly faster generation speed, as well as exact divergence-based likelihood computation. Finally, without any architectural changes, Quetzal natively handles variable-size tasks like hydrogen decoration and scaffold completion. We hope that our work motivates a perspective on scalability and generality for generative modelling of 3D molecules. △ Less

Submitted 19 May, 2025; originally announced May 2025.

Contrastive Alignment with Semantic Gap-Aware Corrections in Text-Video Retrieval

Authors: Jian Xiao, Zijie Song, Jialong Hu, Hao Cheng, Zhenzhen Hu, Jia Li, Richang Hong

Abstract: Recent advances in text-video retrieval have been largely driven by contrastive learning frameworks. However, existing methods overlook a key source of optimization tension: the separation between text and video distributions in the representation space (referred to as the modality gap), and the prevalence of false negatives in batch sampling. These factors lead to conflicting gradients under the… ▽ More Recent advances in text-video retrieval have been largely driven by contrastive learning frameworks. However, existing methods overlook a key source of optimization tension: the separation between text and video distributions in the representation space (referred to as the modality gap), and the prevalence of false negatives in batch sampling. These factors lead to conflicting gradients under the InfoNCE loss, impeding stable alignment. To mitigate this, we propose GARE, a Gap-Aware Retrieval framework that introduces a learnable, pair-specific increment Delta_ij between text t_i and video v_j to offload the tension from the global anchor representation. We first derive the ideal form of Delta_ij via a coupled multivariate first-order Taylor approximation of the InfoNCE loss under a trust-region constraint, revealing it as a mechanism for resolving gradient conflicts by guiding updates along a locally optimal descent direction. Due to the high cost of directly computing Delta_ij, we introduce a lightweight neural module conditioned on the semantic gap between each video-text pair, enabling structure-aware correction guided by gradient supervision. To further stabilize learning and promote interpretability, we regularize Delta using three components: a trust-region constraint to prevent oscillation, a directional diversity term to promote semantic coverage, and an information bottleneck to limit redundancy. Experiments across four retrieval benchmarks show that GARE consistently improves alignment accuracy and robustness to noisy supervision, confirming the effectiveness of gap-aware tension mitigation. △ Less

Submitted 2 June, 2025; v1 submitted 18 May, 2025; originally announced May 2025.

Generalization Guarantees for Learning Branch-and-Cut Policies in Integer Programming

Authors: Hongyu Cheng, Amitabh Basu

Abstract: Mixed-integer programming (MIP) provides a powerful framework for optimization problems, with Branch-and-Cut (B&C) being the predominant algorithm in state-of-the-art solvers. The efficiency of B&C critically depends on heuristic policies for making sequential decisions, including node selection, cut selection, and branching variable selection. While traditional solvers often employ heuristics wit… ▽ More Mixed-integer programming (MIP) provides a powerful framework for optimization problems, with Branch-and-Cut (B&C) being the predominant algorithm in state-of-the-art solvers. The efficiency of B&C critically depends on heuristic policies for making sequential decisions, including node selection, cut selection, and branching variable selection. While traditional solvers often employ heuristics with manually tuned parameters, recent approaches increasingly leverage machine learning, especially neural networks, to learn these policies directly from data. A key challenge is to understand the theoretical underpinnings of these learned policies, particularly their generalization performance from finite data. This paper establishes rigorous sample complexity bounds for learning B&C policies where the scoring functions guiding each decision step (node, cut, branch) have a certain piecewise polynomial structure. This structure generalizes the linear models that form the most commonly deployed policies in practice and investigated recently in a foundational series of theoretical works by Balcan et al. Such piecewise polynomial policies also cover the neural network architectures (e.g., using ReLU activations) that have been the focal point of contemporary practical studies. Consequently, our theoretical framework closely reflects the models utilized by practitioners investigating machine learning within B&C, offering a unifying perspective relevant to both established theory and modern empirical research in this area. Furthermore, our theory applies to quite general sequential decision making problems beyond B&C. △ Less

Submitted 16 May, 2025; originally announced May 2025.

REACT: Runtime-Enabled Active Collision-avoidance Technique for Autonomous Driving

Authors: Heye Huang, Hao Cheng, Zhiyuan Zhou, Zijin Wang, Qichao Liu, Xiaopeng Li

Abstract: Achieving rapid and effective active collision avoidance in dynamic interactive traffic remains a core challenge for autonomous driving. This paper proposes REACT (Runtime-Enabled Active Collision-avoidance Technique), a closed-loop framework that integrates risk assessment with active avoidance control. By leveraging energy transfer principles and human-vehicle-road interaction modeling, REACT dy… ▽ More Achieving rapid and effective active collision avoidance in dynamic interactive traffic remains a core challenge for autonomous driving. This paper proposes REACT (Runtime-Enabled Active Collision-avoidance Technique), a closed-loop framework that integrates risk assessment with active avoidance control. By leveraging energy transfer principles and human-vehicle-road interaction modeling, REACT dynamically quantifies runtime risk and constructs a continuous spatial risk field. The system incorporates physically grounded safety constraints such as directional risk and traffic rules to identify high-risk zones and generate feasible, interpretable avoidance behaviors. A hierarchical warning trigger strategy and lightweight system design enhance runtime efficiency while ensuring real-time responsiveness. Evaluations across four representative high-risk scenarios including car-following braking, cut-in, rear-approaching, and intersection conflict demonstrate REACT's capability to accurately identify critical risks and execute proactive avoidance. Its risk estimation aligns closely with human driver cognition (i.e., warning lead time < 0.4 s), achieving 100% safe avoidance with zero false alarms or missed detections. Furthermore, it exhibits superior real-time performance (< 50 ms latency), strong foresight, and generalization. The lightweight architecture achieves state-of-the-art accuracy, highlighting its potential for real-time deployment in safety-critical autonomous systems. △ Less

Submitted 16 May, 2025; originally announced May 2025.

Comments: 22 pages, 11 figures

Multi-User Beamforming with Deep Reinforcement Learning in Sensing-Aided Communication

Authors: Xiyu Wang, Gilberto Berardinelli, Hei Victor Cheng, Petar Popovski, Ramoni Adeogun

Abstract: Mobile users are prone to experience beam failure due to beam drifting in millimeter wave (mmWave) communications. Sensing can help alleviate beam drifting with timely beam changes and low overhead since it does not need user feedback. This work studies the problem of optimizing sensing-aided communication by dynamically managing beams allocated to mobile users. A multi-beam scheme is introduced,… ▽ More Mobile users are prone to experience beam failure due to beam drifting in millimeter wave (mmWave) communications. Sensing can help alleviate beam drifting with timely beam changes and low overhead since it does not need user feedback. This work studies the problem of optimizing sensing-aided communication by dynamically managing beams allocated to mobile users. A multi-beam scheme is introduced, which allocates multiple beams to the users that need an update on the angle of departure (AoD) estimates and a single beam to the users that have satisfied AoD estimation precision. A deep reinforcement learning (DRL) assisted method is developed to optimize the beam allocation policy, relying only upon the sensing echoes. For comparison, a heuristic AoD-based method using approximated Cramér-Rao lower bound (CRLB) for allocation is also presented. Both methods require neither user feedback nor prior state evolution information. Results show that the DRL-assisted method achieves a considerable gain in throughput than the conventional beam sweeping method and the AoD-based method, and it is robust to different user speeds. △ Less

Submitted 9 May, 2025; originally announced May 2025.

Comments: Accepted for Presentation at IEEE EuCNC & 6G Summit 2025

Occupancy World Model for Robots

Authors: Zhang Zhang, Qiang Zhang, Wei Cui, Shuai Shi, Yijie Guo, Gang Han, Wen Zhao, Jingkai Sun, Jiahang Cao, Jiaxu Wang, Hao Cheng, Xiaozhu Ju, Zhengping Che, Renjing Xu, Jian Tang

Abstract: Understanding and forecasting the scene evolutions deeply affect the exploration and decision of embodied agents. While traditional methods simulate scene evolutions through trajectory prediction of potential instances, current works use the occupancy world model as a generative framework for describing fine-grained overall scene dynamics. However, existing methods cluster on the outdoor structure… ▽ More Understanding and forecasting the scene evolutions deeply affect the exploration and decision of embodied agents. While traditional methods simulate scene evolutions through trajectory prediction of potential instances, current works use the occupancy world model as a generative framework for describing fine-grained overall scene dynamics. However, existing methods cluster on the outdoor structured road scenes, while ignoring the exploration of forecasting 3D occupancy scene evolutions for robots in indoor scenes. In this work, we explore a new framework for learning the scene evolutions of observed fine-grained occupancy and propose an occupancy world model based on the combined spatio-temporal receptive field and guided autoregressive transformer to forecast the scene evolutions, called RoboOccWorld. We propose the Conditional Causal State Attention (CCSA), which utilizes camera poses of next state as conditions to guide the autoregressive transformer to adapt and understand the indoor robotics scenarios. In order to effectively exploit the spatio-temporal cues from historical observations, Hybrid Spatio-Temporal Aggregation (HSTA) is proposed to obtain the combined spatio-temporal receptive field based on multi-scale spatio-temporal windows. In addition, we restructure the OccWorld-ScanNet benchmark based on local annotations to facilitate the evaluation of the indoor 3D occupancy scene evolution prediction task. Experimental results demonstrate that our RoboOccWorld outperforms state-of-the-art methods in indoor 3D occupancy scene evolution prediction task. The code will be released soon. △ Less

Submitted 7 May, 2025; originally announced May 2025.

Learning Real Facial Concepts for Independent Deepfake Detection

Authors: Ming-Hui Liu, Harry Cheng, Tianyi Wang, Xin Luo, Xin-Shun Xu

Abstract: Deepfake detection models often struggle with generalization to unseen datasets, manifesting as misclassifying real instances as fake in target domains. This is primarily due to an overreliance on forgery artifacts and a limited understanding of real faces. To address this challenge, we propose a novel approach RealID to enhance generalization by learning a comprehensive concept of real faces whil… ▽ More Deepfake detection models often struggle with generalization to unseen datasets, manifesting as misclassifying real instances as fake in target domains. This is primarily due to an overreliance on forgery artifacts and a limited understanding of real faces. To address this challenge, we propose a novel approach RealID to enhance generalization by learning a comprehensive concept of real faces while assessing the probabilities of belonging to the real and fake classes independently. RealID comprises two key modules: the Real Concept Capture Module (RealC2) and the Independent Dual-Decision Classifier (IDC). With the assistance of a MultiReal Memory, RealC2 maintains various prototypes for real faces, allowing the model to capture a comprehensive concept of real class. Meanwhile, IDC redefines the classification strategy by making independent decisions based on the concept of the real class and the presence of forgery artifacts. Through the combined effect of the above modules, the influence of forgery-irrelevant patterns is alleviated, and extensive experiments on five widely used datasets demonstrate that RealID significantly outperforms existing state-of-the-art methods, achieving a 1.74% improvement in average accuracy. △ Less

Submitted 7 May, 2025; originally announced May 2025.

Comments: Accepted by IJCAI 2025

Automated Action Generation based on Action Field for Robotic Garment Manipulation

Authors: Hu Cheng, Fuyuki Tokuda, Kazuhiro Kosuge

Abstract: Garment manipulation using robotic systems is a challenging task due to the diverse shapes and deformable nature of fabric. In this paper, we propose a novel method for robotic garment manipulation that significantly improves the accuracy while reducing computational time compared to previous approaches. Our method features an action generator that directly interprets scene images and generates pi… ▽ More Garment manipulation using robotic systems is a challenging task due to the diverse shapes and deformable nature of fabric. In this paper, we propose a novel method for robotic garment manipulation that significantly improves the accuracy while reducing computational time compared to previous approaches. Our method features an action generator that directly interprets scene images and generates pixel-wise end-effector action vectors using a neural network. The network also predicts a manipulation score map that ranks potential actions, allowing the system to select the most effective action. Extensive simulation experiments demonstrate that our method achieves higher unfolding and alignment performances and faster computation time than previous approaches. Real-world experiments show that the proposed method generalizes well to different garment types and successfully flattens garments. △ Less

Submitted 6 May, 2025; originally announced May 2025.

Optimization of Module Transferability in Single Image Super-Resolution: Universality Assessment and Cycle Residual Blocks

Authors: Haotong Cheng, Zhiqi Zhang, Hao Li, Xinshang Zhang

Abstract: Deep learning has substantially advanced the Single Image Super-Resolution (SISR). However, existing researches have predominantly focused on raw performance gains, with little attention paid to quantifying the transferability of architectural components. In this paper, we introduce the concept of "Universality" and its associated definitions which extend the traditional notion of "Generalization"… ▽ More Deep learning has substantially advanced the Single Image Super-Resolution (SISR). However, existing researches have predominantly focused on raw performance gains, with little attention paid to quantifying the transferability of architectural components. In this paper, we introduce the concept of "Universality" and its associated definitions which extend the traditional notion of "Generalization" to encompass the modules' ease of transferability, thus revealing the relationships between module universality and model generalizability. Then we propose the Universality Assessment Equation (UAE), a metric for quantifying how readily a given module could be transplanted across models. Guided by the UAE results of standard residual blocks and other plug-and-play modules, we further design two optimized modules, Cycle Residual Block (CRB) and Depth-Wise Cycle Residual Block (DCRB). Through comprehensive experiments on natural-scene benchmarks, remote-sensing datasets, extreme-industrial imagery and on-device deployments, we demonstrate that networks embedded with the proposed plug-and-play modules outperform several state-of-the-arts, reaching a PSNR enhancement of up to 0.83dB or enabling a 71.3% reduction in parameters with negligible loss in reconstruction fidelity. △ Less

Submitted 6 May, 2025; originally announced May 2025.

RIFT: Closed-Loop RL Fine-Tuning for Realistic and Controllable Traffic Simulation

Authors: Keyu Chen, Wenchao Sun, Hao Cheng, Sifa Zheng

Abstract: Achieving both realism and controllability in interactive closed-loop traffic simulation remains a key challenge in autonomous driving. Data-driven simulation methods reproduce realistic trajectories but suffer from covariate shift in closed-loop deployment, compounded by simplified dynamics models that further reduce reliability. Conversely, physics-based simulation methods enhance reliable and c… ▽ More Achieving both realism and controllability in interactive closed-loop traffic simulation remains a key challenge in autonomous driving. Data-driven simulation methods reproduce realistic trajectories but suffer from covariate shift in closed-loop deployment, compounded by simplified dynamics models that further reduce reliability. Conversely, physics-based simulation methods enhance reliable and controllable closed-loop interactions but often lack expert demonstrations, compromising realism. To address these challenges, we introduce a dual-stage AV-centered simulation framework that conducts open-loop imitation learning pre-training in a data-driven simulator to capture trajectory-level realism and multimodality, followed by closed-loop reinforcement learning fine-tuning in a physics-based simulator to enhance controllability and mitigate covariate shift. In the fine-tuning stage, we propose RIFT, a simple yet effective closed-loop RL fine-tuning strategy that preserves the trajectory-level multimodality through a GRPO-style group-relative advantage formulation, while enhancing controllability and training stability by replacing KL regularization with the dual-clip mechanism. Extensive experiments demonstrate that RIFT significantly improves the realism and controllability of generated traffic scenarios, providing a robust platform for evaluating autonomous vehicle performance in diverse and interactive scenarios. △ Less

Submitted 6 May, 2025; originally announced May 2025.

El Agente: An Autonomous Agent for Quantum Chemistry

Authors: Yunheng Zou, Austin H. Cheng, Abdulrahman Aldossary, Jiaru Bai, Shi Xuan Leong, Jorge Arturo Campos-Gonzalez-Angulo, Changhyeok Choi, Cher Tian Ser, Gary Tom, Andrew Wang, Zijian Zhang, Ilya Yakavets, Han Hao, Chris Crebolder, Varinia Bernales, Alán Aspuru-Guzik

Abstract: Computational chemistry tools are widely used to study the behaviour of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is bui… ▽ More Computational chemistry tools are widely used to study the behaviour of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is built on a novel cognitive architecture featuring a hierarchical memory framework that enables flexible task decomposition, adaptive tool selection, post-analysis, and autonomous file handling and submission. El Agente Q is benchmarked on six university-level course exercises and two case studies, demonstrating robust problem-solving performance (averaging >87% task success) and adaptive error handling through in situ debugging. It also supports longer-term, multi-step task execution for more complex workflows, while maintaining transparency through detailed action trace logs. Together, these capabilities lay the foundation for increasingly autonomous and accessible quantum chemistry. △ Less

Submitted 5 May, 2025; originally announced May 2025.

VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection

Authors: Hao Cheng, Zhiwei Zhao, Yichao He, Zhenzhen Hu, Jia Li, Meng Wang, Richang Hong

Abstract: Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced s… ▽ More Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced strong multimodal representations, yet they predominantly rely on modality-specific encoders and coarse content-level alignment, limiting fine-grained emotional semantic modeling. To address these issues, we propose VAEmo, an efficient two-stage framework for emotion-centric joint VA representation learning with external knowledge injection. In Stage 1, a unified and lightweight representation network is pre-trained on large-scale speaker-centric VA corpora via masked reconstruction and contrastive objectives, mitigating the modality gap and learning expressive, complementary representations without emotion labels. In Stage 2, multimodal large language models automatically generate detailed affective descriptions according to our well-designed chain-of-thought prompting for only a small subset of VA samples; these rich textual semantics are then injected by aligning their corresponding embeddings with VA representations through dual-path contrastive learning, further bridging the emotion gap. Extensive experiments on multiple downstream AVER benchmarks show that VAEmo achieves state-of-the-art performance with a compact design, highlighting the benefit of unified cross-modal encoding and emotion-aware semantic guidance for efficient, generalizable VA emotion representations. △ Less

Submitted 4 May, 2025; originally announced May 2025.

Comments: Source code and pre-trained models will be available at https://github.com/MSA-LMC/VAEmo

T-Graph: Enhancing Sparse-view Camera Pose Estimation by Pairwise Translation Graph

Authors: Qingyu Xian, Weiqin Jiao, Hao Cheng, Berend Jan van der Zwaag, Yanqiu Huang

Abstract: Sparse-view camera pose estimation, which aims to estimate the 6-Degree-of-Freedom (6-DoF) poses from a limited number of images captured from different viewpoints, is a fundamental yet challenging problem in remote sensing applications. Existing methods often overlook the translation information between each pair of viewpoints, leading to suboptimal performance in sparse-view scenarios. To addres… ▽ More Sparse-view camera pose estimation, which aims to estimate the 6-Degree-of-Freedom (6-DoF) poses from a limited number of images captured from different viewpoints, is a fundamental yet challenging problem in remote sensing applications. Existing methods often overlook the translation information between each pair of viewpoints, leading to suboptimal performance in sparse-view scenarios. To address this limitation, we introduce T-Graph, a lightweight, plug-and-play module to enhance camera pose estimation in sparse-view settings. T-graph takes paired image features as input and maps them through a Multilayer Perceptron (MLP). It then constructs a fully connected translation graph, where nodes represent cameras and edges encode their translation relationships. It can be seamlessly integrated into existing models as an additional branch in parallel with the original prediction, maintaining efficiency and ease of use. Furthermore, we introduce two pairwise translation representations, relative-t and pair-t, formulated under different local coordinate systems. While relative-t captures intuitive spatial relationships, pair-t offers a rotation-disentangled alternative. The two representations contribute to enhanced adaptability across diverse application scenarios, further improving our module's robustness. Extensive experiments on two state-of-the-art methods (RelPose++ and Forge) using public datasets (C03D and IMC PhotoTourism) validate both the effectiveness and generalizability of T-Graph. The results demonstrate consistent improvements across various metrics, notably camera center accuracy, which improves by 1% to 6% from 2 to 8 viewpoints. △ Less

Submitted 2 May, 2025; originally announced May 2025.

LDPoly: Latent Diffusion for Polygonal Road Outline Extraction in Large-Scale Topographic Mapping

Authors: Weiqin Jiao, Hao Cheng, George Vosselman, Claudio Persello

Abstract: Polygonal road outline extraction from high-resolution aerial images is an important task in large-scale topographic mapping, where roads are represented as vectorized polygons, capturing essential geometric features with minimal vertex redundancy. Despite its importance, no existing method has been explicitly designed for this task. While polygonal building outline extraction has been extensively… ▽ More Polygonal road outline extraction from high-resolution aerial images is an important task in large-scale topographic mapping, where roads are represented as vectorized polygons, capturing essential geometric features with minimal vertex redundancy. Despite its importance, no existing method has been explicitly designed for this task. While polygonal building outline extraction has been extensively studied, the unique characteristics of roads, such as branching structures and topological connectivity, pose challenges to these methods. To address this gap, we introduce LDPoly, the first dedicated framework for extracting polygonal road outlines from high-resolution aerial images. Our method leverages a novel Dual-Latent Diffusion Model with a Channel-Embedded Fusion Module, enabling the model to simultaneously generate road masks and vertex heatmaps. A tailored polygonization method is then applied to obtain accurate vectorized road polygons with minimal vertex redundancy. We evaluate LDPoly on a new benchmark dataset, Map2ImLas, which contains detailed polygonal annotations for various topographic objects in several Dutch regions. Our experiments include both in-region and cross-region evaluations, with the latter designed to assess the model's generalization performance on unseen regions. Quantitative and qualitative results demonstrate that LDPoly outperforms state-of-the-art polygon extraction methods across various metrics, including pixel-level coverage, vertex efficiency, polygon regularity, and road connectivity. We also design two new metrics to assess polygon simplicity and boundary smoothness. Moreover, this work represents the first application of diffusion models for extracting precise vectorized object outlines without redundant vertices from remote-sensing imagery, paving the way for future advancements in this field. △ Less

Submitted 29 April, 2025; originally announced April 2025.