Showing 1–50 of 383 results for author: Han, W

Asymmetric Lesion Detection with Geometric Patterns and CNN-SVM Classification

Authors: M. A. Rasel, Sameem Abdul Kareem, Zhenli Kwan, Nik Aimee Azizah Faheem, Winn Hui Han, Rebecca Kai Jan Choong, Shin Shen Yong, Unaizah Obaidellah

Abstract: In dermoscopic images, which allow visualization of surface skin structures not visible to the naked eye, lesion shape offers vital insights into skin diseases. In clinically practiced methods, asymmetric lesion shape is one of the criteria for diagnosing melanoma. Initially, we labeled data for a non-annotated dataset with symmetrical information based on clinical assessments. Subsequently, we pr… ▽ More In dermoscopic images, which allow visualization of surface skin structures not visible to the naked eye, lesion shape offers vital insights into skin diseases. In clinically practiced methods, asymmetric lesion shape is one of the criteria for diagnosing melanoma. Initially, we labeled data for a non-annotated dataset with symmetrical information based on clinical assessments. Subsequently, we propose a supporting technique, a supervised learning image processing algorithm, to analyze the geometrical pattern of lesion shape, aiding non-experts in understanding the criteria of an asymmetric lesion. We then utilize a pre-trained convolutional neural network (CNN) to extract shape, color, and texture features from dermoscopic images for training a multiclass support vector machine (SVM) classifier, outperforming state-of-the-art methods from the literature. In the geometry-based experiment, we achieved a 99.00% detection rate for dermatological asymmetric lesions. In the CNN-based experiment, the best performance is found with 94% Kappa Score, 95% Macro F1-score, and 97% Weighted F1-score for classifying lesion shapes (Asymmetric, Half-Symmetric, and Symmetric). △ Less

Submitted 23 July, 2025; originally announced July 2025.

Comments: Accepted version. Published in Computers in Biology and Medicine, Volume 179, 2024. DOI: 10.1016/j.compbiomed.2024.108851

Journal ref: Computers in Biology and Medicine, Volume 179, 2024, Article 108851

Routine: A Structural Planning Framework for LLM Agent System in Enterprise

Authors: Guancheng Zeng, Xueyi Chen, Jiawang Hu, Shaohua Qi, Yaxuan Mao, Zhantao Wang, Yifan Nie, Shuang Li, Qiuyang Feng, Pengxu Qiu, Yujia Wang, Wenqiang Han, Linyan Huang, Gang Li, Jingjing Mo, Haowen Hu

Abstract: The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To address this, this paper introduces Routine, a multi-step agent planning framework designed with a clear structure, explicit instructions, and seamless parameter… ▽ More The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To address this, this paper introduces Routine, a multi-step agent planning framework designed with a clear structure, explicit instructions, and seamless parameter passing to guide the agent's execution module in performing multi-step tool-calling tasks with high stability. In evaluations conducted within a real-world enterprise scenario, Routine significantly increases the execution accuracy in model tool calls, increasing the performance of GPT-4o from 41.1% to 96.3%, and Qwen3-14B from 32.6% to 83.3%. We further constructed a Routine-following training dataset and fine-tuned Qwen3-14B, resulting in an accuracy increase to 88.2% on scenario-specific evaluations, indicating improved adherence to execution plans. In addition, we employed Routine-based distillation to create a scenario-specific, multi-step tool-calling dataset. Fine-tuning on this distilled dataset raised the model's accuracy to 95.5%, approaching GPT-4o's performance. These results highlight Routine's effectiveness in distilling domain-specific tool-usage patterns and enhancing model adaptability to new scenarios. Our experimental results demonstrate that Routine provides a practical and accessible approach to building stable agent workflows, accelerating the deployment and adoption of agent systems in enterprise environments, and advancing the technical vision of AI for Process. △ Less

Submitted 22 July, 2025; v1 submitted 18 July, 2025; originally announced July 2025.

Comments: 26 pages, 8 figures, 5 tables

Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration

Authors: Wenkang Han, Wang Lin, Yiyun Zhou, Qi Liu, Shulei Wang, Chang Yao, Jingyuan Chen

Abstract: Face Video Restoration (FVR) aims to recover high-quality face videos from degraded versions. Traditional methods struggle to preserve fine-grained, identity-specific features when degradation is severe, often producing average-looking faces that lack individual characteristics. To address these challenges, we introduce IP-FVR, a novel method that leverages a high-quality reference face image as a… ▽ More Face Video Restoration (FVR) aims to recover high-quality face videos from degraded versions. Traditional methods struggle to preserve fine-grained, identity-specific features when degradation is severe, often producing average-looking faces that lack individual characteristics. To address these challenges, we introduce IP-FVR, a novel method that leverages a high-quality reference face image as a visual prompt to provide identity conditioning during the denoising process. IP-FVR incorporates semantically rich identity information from the reference image using decoupled cross-attention mechanisms, ensuring detailed and identity consistent results. For intra-clip identity drift (within 24 frames), we introduce an identity-preserving feedback learning method that combines cosine similarity-based reward signals with suffix-weighted temporal aggregation. This approach effectively minimizes drift within sequences of frames. For inter-clip identity drift, we develop an exponential blending strategy that aligns identities across clips by iteratively blending frames from previous clips during the denoising process. This method ensures consistent identity representation across different clips. Additionally, we enhance the restoration process with a multi-stream negative prompt, guiding the model's attention to relevant facial attributes and minimizing the generation of low-quality or incorrect features. Extensive experiments on both synthetic and real-world datasets demonstrate that IP-FVR outperforms existing methods in both quality and identity preservation, showcasing its substantial potential for practical applications in face video restoration. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Comments: Accepted by MM 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

Leveraging Out-of-Distribution Unlabeled Images: Semi-Supervised Semantic Segmentation with an Open-Vocabulary Model

Authors: Wooseok Shin, Jisu Kang, Hyeonki Jeong, Jin Sob Kim, Sung Won Han

Abstract: In semi-supervised semantic segmentation, existing studies have shown promising results in academic settings with controlled splits of benchmark datasets. However, the potential benefits of leveraging significantly larger sets of unlabeled images remain unexplored. In real-world scenarios, abundant unlabeled images are often available from online sources (web-scraped images) or large-scale dataset… ▽ More In semi-supervised semantic segmentation, existing studies have shown promising results in academic settings with controlled splits of benchmark datasets. However, the potential benefits of leveraging significantly larger sets of unlabeled images remain unexplored. In real-world scenarios, abundant unlabeled images are often available from online sources (web-scraped images) or large-scale datasets. However, these images may have different distributions from those of the target dataset, a situation known as out-of-distribution (OOD). Using these images as unlabeled data in semi-supervised learning can lead to inaccurate pseudo-labels, potentially misguiding network training. In this paper, we propose a new semi-supervised semantic segmentation framework with an open-vocabulary segmentation model (SemiOVS) to effectively utilize unlabeled OOD images. Extensive experiments on Pascal VOC and Context datasets demonstrate two key findings: (1) using additional unlabeled images improves the performance of semi-supervised learners in scenarios with few labels, and (2) using the open-vocabulary segmentation (OVS) model to pseudo-label OOD images leads to substantial performance gains. In particular, SemiOVS outperforms existing PrevMatch and SemiVL methods by +3.5 and +3.0 mIoU, respectively, on Pascal VOC with a 92-label setting, achieving state-of-the-art performance. These findings demonstrate that our approach effectively utilizes abundant unlabeled OOD images for semantic segmentation tasks. We hope this work can inspire future research and real-world applications. The code is available at https://github.com/wooseok-shin/SemiOVS △ Less

Submitted 4 July, 2025; originally announced July 2025.

Comments: 19pages, 8 figures

Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis

Authors: Byung Hyun Lee, Wongi Jeong, Woojae Han, Kyoungbun Lee, Se Young Chun

Abstract: Multiple instance learning (MIL) significantly reduced annotation costs via bag-level weak labels for large-scale images, such as histopathological whole slide images (WSIs). However, its adaptability to continual tasks with minimal forgetting has been rarely explored, especially on instance classification for localization. Weakly incremental learning for semantic segmentation has been studied for… ▽ More Multiple instance learning (MIL) significantly reduced annotation costs via bag-level weak labels for large-scale images, such as histopathological whole slide images (WSIs). However, its adaptability to continual tasks with minimal forgetting has been rarely explored, especially on instance classification for localization. Weakly incremental learning for semantic segmentation has been studied for continual localization, but it focused on natural images, leveraging global relationships among hundreds of small patches (e.g., $16 \times 16$) using pre-trained models. This approach seems infeasible for MIL localization due to enormous amounts ($\sim 10^5$) of large patches (e.g., $256 \times 256$) and no available global relationships such as cancer cells. To address these challenges, we propose Continual Multiple Instance Learning with Enhanced Localization (CoMEL), an MIL framework for both localization and adaptability with minimal forgetting. CoMEL consists of (1) Grouped Double Attention Transformer (GDAT) for efficient instance encoding, (2) Bag Prototypes-based Pseudo-Labeling (BPPL) for reliable instance pseudo-labeling, and (3) Orthogonal Weighted Low-Rank Adaptation (OWLoRA) to mitigate forgetting in both bag and instance classification. Extensive experiments on three public WSI datasets demonstrate superior performance of CoMEL, outperforming the prior arts by up to $11.00\%$ in bag-level accuracy and up to $23.4\%$ in localization accuracy under the continual MIL setup. △ Less

Submitted 8 July, 2025; v1 submitted 3 July, 2025; originally announced July 2025.

Comments: Accepted at ICCV 2025

MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining

Authors: Zhixun Chen, Ping Guo, Wenhan Han, Yifan Zhang, Binbin Liu, Haobin Lin, Fengze Liu, Yan Zhao, Bingni Zhang, Taifeng Wang, Yin Zheng, Meng Fang

Abstract: Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on English. We introduce MuRating, a scalable framework that transfers high-quality English data-quality signals into a single rater for 17 target languages. MuRating aggregates multiple English "raters" via pairwise comparisons to learn unified document-qualit… ▽ More Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on English. We introduce MuRating, a scalable framework that transfers high-quality English data-quality signals into a single rater for 17 target languages. MuRating aggregates multiple English "raters" via pairwise comparisons to learn unified document-quality scores,then projects these judgments through translation to train a multilingual evaluator on monolingual, cross-lingual, and parallel text pairs. Applied to web data, MuRating selects balanced subsets of English and multilingual content to pretrain a 1.2 B-parameter LLaMA model. Compared to strong baselines, including QuRater, AskLLM, DCLM and so on, our approach boosts average accuracy on both English benchmarks and multilingual evaluations, with especially large gains on knowledge-intensive tasks. We further analyze translation fidelity, selection biases, and underrepresentation of narrative material, outlining directions for future work. △ Less

Submitted 2 July, 2025; originally announced July 2025.

MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages

Authors: Wenhan Han, Yifan Zhang, Zhixun Chen, Binbin Liu, Haobin Lin, Bingni Zhang, Taifeng Wang, Mykola Pechenizkiy, Meng Fang, Yin Zheng

Abstract: Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation datasets are limited and lack cross-lingual alignment, leaving assessments of multilingual capabilities fragmented in both language and skill coverage. To address this, we introduce MuBench, a benchmark covering 61 language… ▽ More Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation datasets are limited and lack cross-lingual alignment, leaving assessments of multilingual capabilities fragmented in both language and skill coverage. To address this, we introduce MuBench, a benchmark covering 61 languages and evaluating a broad range of capabilities. We evaluate several state-of-the-art multilingual LLMs and find notable gaps between claimed and actual language coverage, particularly a persistent performance disparity between English and low-resource languages. Leveraging MuBench's alignment, we propose Multilingual Consistency (MLC) as a complementary metric to accuracy for analyzing performance bottlenecks and guiding model improvement. Finally, we pretrain a suite of 1.2B-parameter models on English and Chinese with 500B tokens, varying language ratios and parallel data proportions to investigate cross-lingual transfer dynamics. △ Less

Submitted 24 June, 2025; originally announced June 2025.

Enhancing Stress-Strain Predictions with Seq2Seq and Cross-Attention based on Small Punch Test

Authors: Zhengni Yang, Rui Yang, Weijian Han, Qixin Liu

Abstract: This paper introduces a novel deep-learning approach to predict true stress-strain curves of high-strength steels from small punch test (SPT) load-displacement data. The proposed approach uses Gramian Angular Field (GAF) to transform load-displacement sequences into images, capturing spatial-temporal features and employs a Sequence-to-Sequence (Seq2Seq) model with an LSTM-based encoder-decoder arc… ▽ More This paper introduces a novel deep-learning approach to predict true stress-strain curves of high-strength steels from small punch test (SPT) load-displacement data. The proposed approach uses Gramian Angular Field (GAF) to transform load-displacement sequences into images, capturing spatial-temporal features and employs a Sequence-to-Sequence (Seq2Seq) model with an LSTM-based encoder-decoder architecture, enhanced by multi-head cross-attention to improved accuracy. Experimental results demonstrate that the proposed approach achieves superior prediction accuracy, with minimum and maximum mean absolute errors of 0.15 MPa and 5.58 MPa, respectively. The proposed method offers a promising alternative to traditional experimental techniques in materials science, enhancing the accuracy and efficiency of true stress-strain relationship predictions. △ Less

Submitted 21 June, 2025; originally announced June 2025.

Comments: accepted by IJCNN2025

RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching

Authors: Hyun Joon Park, Jeongmin Liu, Jin Sob Kim, Jeong Yeol Yang, Sung Won Han, Eunwoo Song

Abstract: We introduce RapFlow-TTS, a rapid and high-fidelity TTS acoustic model that leverages velocity consistency constraints in flow matching (FM) training. Although ordinary differential equation (ODE)-based TTS generation achieves natural-quality speech, it typically requires a large number of generation steps, resulting in a trade-off between quality and inference speed. To address this challenge, Ra… ▽ More We introduce RapFlow-TTS, a rapid and high-fidelity TTS acoustic model that leverages velocity consistency constraints in flow matching (FM) training. Although ordinary differential equation (ODE)-based TTS generation achieves natural-quality speech, it typically requires a large number of generation steps, resulting in a trade-off between quality and inference speed. To address this challenge, RapFlow-TTS enforces consistency in the velocity field along the FM-straightened ODE trajectory, enabling consistent synthetic quality with fewer generation steps. Additionally, we introduce techniques such as time interval scheduling and adversarial learning to further enhance the quality of the few-step synthesis. Experimental results show that RapFlow-TTS achieves high-fidelity speech synthesis with a 5- and 10-fold reduction in synthesis steps than the conventional FM- and score-based approaches, respectively. △ Less

Submitted 20 June, 2025; originally announced June 2025.

Comments: Accepted on Interspeech 2025

TD3Net: A Temporal Densely Connected Multi-Dilated Convolutional Network for Lipreading

Authors: Byung Hoon Lee, Wooseok Shin, Sung Won Han

Abstract: The word-level lipreading approach typically employs a two-stage framework with separate frontend and backend architectures to model dynamic lip movements. Each component has been extensively studied, and in the backend architecture, temporal convolutional networks (TCNs) have been widely adopted in state-of-the-art methods. Recently, dense skip connections have been introduced in TCNs to mitigate… ▽ More The word-level lipreading approach typically employs a two-stage framework with separate frontend and backend architectures to model dynamic lip movements. Each component has been extensively studied, and in the backend architecture, temporal convolutional networks (TCNs) have been widely adopted in state-of-the-art methods. Recently, dense skip connections have been introduced in TCNs to mitigate the limited density of the receptive field, thereby improving the modeling of complex temporal representations. However, their performance remains constrained owing to potential information loss regarding the continuous nature of lip movements, caused by blind spots in the receptive field. To address this limitation, we propose TD3Net, a temporal densely connected multi-dilated convolutional network that combines dense skip connections and multi-dilated temporal convolutions as the backend architecture. TD3Net covers a wide and dense receptive field without blind spots by applying different dilation factors to skip-connected features. Experimental results on a word-level lipreading task using two large publicly available datasets, Lip Reading in the Wild (LRW) and LRW-1000, indicate that the proposed method achieves performance comparable to state-of-the-art methods. It achieved higher accuracy with fewer parameters and lower floating-point operations compared to existing TCN-based backend architectures. Moreover, visualization results suggest that our approach effectively utilizes diverse temporal features while preserving temporal continuity, presenting notable advantages in lipreading systems. The code is available at our GitHub repository: https://github.com/Leebh-kor/TD3Net-A-Temporal-Densely-Connected-Multi-dilated-Convolutional-Network-for-Lipreading △ Less

Submitted 19 June, 2025; originally announced June 2025.

Comments: 15 pages, 6 figures

ACM Class: I.4.8; I.5.4; I.2.10

MoNetV2: Enhanced Motion Network for Freehand 3D Ultrasound Reconstruction

Authors: Mingyuan Luo, Xin Yang, Zhongnuo Yan, Yan Cao, Yuanji Zhang, Xindi Hu, Jin Wang, Haoxuan Ding, Wei Han, Litao Sun, Dong Ni

Abstract: Three-dimensional (3D) ultrasound (US) aims to provide sonographers with the spatial relationships of anatomical structures, playing a crucial role in clinical diagnosis. Recently, deep-learning-based freehand 3D US has made significant advancements. It reconstructs volumes by estimating transformations between images without external tracking. However, image-only reconstruction poses difficulties… ▽ More Three-dimensional (3D) ultrasound (US) aims to provide sonographers with the spatial relationships of anatomical structures, playing a crucial role in clinical diagnosis. Recently, deep-learning-based freehand 3D US has made significant advancements. It reconstructs volumes by estimating transformations between images without external tracking. However, image-only reconstruction poses difficulties in reducing cumulative drift and further improving reconstruction accuracy, particularly in scenarios involving complex motion trajectories. In this context, we propose an enhanced motion network (MoNetV2) to enhance the accuracy and generalizability of reconstruction under diverse scanning velocities and tactics. First, we propose a sensor-based temporal and multi-branch structure that fuses image and motion information from a velocity perspective to improve image-only reconstruction accuracy. Second, we devise an online multi-level consistency constraint that exploits the inherent consistency of scans to handle various scanning velocities and tactics. This constraint exploits both scan-level velocity consistency, path-level appearance consistency, and patch-level motion consistency to supervise inter-frame transformation estimation. Third, we distill an online multi-modal self-supervised strategy that leverages the correlation between network estimation and motion information to further reduce cumulative errors. Extensive experiments clearly demonstrate that MoNetV2 surpasses existing methods in both reconstruction quality and generalizability performance across three large datasets. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Bounded Memory in Distributed Networks

Authors: Ran Ben Basat, Keren Censor-Hillel, Yi-Jun Chang, Wenchen Han, Dean Leitersdorf, Gregory Schwartzman

Abstract: The recent advent of programmable switches makes distributed algorithms readily deployable in real-world datacenter networks. However, there are still gaps between theory and practice that prevent the smooth adaptation of CONGEST algorithms to these environments. In this paper, we focus on the memory restrictions that arise in real-world deployments. We introduce the $μ$-CONGEST model where on top… ▽ More The recent advent of programmable switches makes distributed algorithms readily deployable in real-world datacenter networks. However, there are still gaps between theory and practice that prevent the smooth adaptation of CONGEST algorithms to these environments. In this paper, we focus on the memory restrictions that arise in real-world deployments. We introduce the $μ$-CONGEST model where on top of the bandwidth restriction, the memory of nodes is also limited to $μ$ words, in line with real-world systems. We provide fast algorithms of two main flavors. First, we observe that many algorithms in the CONGEST model are memory-intensive and do not work in $μ$-CONGEST. A prime example of a family of algorithms that use large memory is clique-listing algorithms. We show that the memory issue that arises here cannot be resolved without incurring a cost in the round complexity, by establishing a lower bound on the round complexity of listing cliques in $μ$-CONGEST. We introduce novel techniques to overcome these issues and generalize the algorithms to work within a given memory bound. Combined with our lower bound, these provide tight tradeoffs between the running time and memory of nodes. Second, we show that it is possible to efficiently simulate various families of streaming algorithms in $μ$-CONGEST. These include fast simulations of $p$-pass algorithms, random order streams, and various types of mergeable streaming algorithms. Combining our contributions, we show that we can use streaming algorithms to efficiently generate statistics regarding combinatorial structures in the network. An example of an end result of this type is that we can efficiently identify and provide the per-color frequencies of the frequent monochromatic triangles in $μ$-CONGEST. △ Less

Submitted 13 June, 2025; originally announced June 2025.

Comments: Accepted at The 37th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA '25). 22 pages

GUIRoboTron-Speech: Towards Automated GUI Agents Based on Speech Instructions

Authors: Wenkang Han, Zhixiong Zeng, Jing Huang, Shu Jiang, Liming Zheng, Longrong Yang, Haibo Qiu, Chang Yao, Jingyuan Chen, Lin Ma

Abstract: Autonomous agents for Graphical User Interfaces (GUIs) are revolutionizing human-computer interaction, yet their reliance on text-based instructions imposes limitations on accessibility and convenience, particularly in hands-free scenarios. To address this gap, we propose GUIRoboTron-Speech, the first end-to-end autonomous GUI agent that directly accepts speech instructions and on-device screensho… ▽ More Autonomous agents for Graphical User Interfaces (GUIs) are revolutionizing human-computer interaction, yet their reliance on text-based instructions imposes limitations on accessibility and convenience, particularly in hands-free scenarios. To address this gap, we propose GUIRoboTron-Speech, the first end-to-end autonomous GUI agent that directly accepts speech instructions and on-device screenshots to predict actions. Confronted with the scarcity of speech-based GUI agent datasets, we initially generated high-quality speech instructions for training by leveraging a random timbre text-to-speech (TTS) model to convert existing text instructions. We then develop GUIRoboTron-Speech's capabilities through progressive grounding and planning training stages. A key contribution is a heuristic mixed-instruction training strategy designed to mitigate the modality imbalance inherent in pre-trained foundation models. Comprehensive experiments on several benchmark datasets validate the robust and superior performance of GUIRoboTron-Speech, demonstrating the significant potential and widespread applicability of speech as an effective instruction modality for driving GUI agents. Our code and datasets are available at https://github.com/GUIRoboTron/GUIRoboTron-Speech. △ Less

Submitted 10 June, 2025; originally announced June 2025.

SlotPi: Physics-informed Object-centric Reasoning Models

Authors: Jian Li, Wan Han, Ning Lin, Yu-Liang Zhan, Ruizhi Chengze, Haining Wang, Yi Zhang, Hongsheng Liu, Zidong Wang, Fan Yu, Hao Sun

Abstract: Understanding and reasoning about dynamics governed by physical laws through visual observation, akin to human capabilities in the real world, poses significant challenges. Currently, object-centric dynamic simulation methods, which emulate human behavior, have achieved notable progress but overlook two critical aspects: 1) the integration of physical knowledge into models. Humans gain physical in… ▽ More Understanding and reasoning about dynamics governed by physical laws through visual observation, akin to human capabilities in the real world, poses significant challenges. Currently, object-centric dynamic simulation methods, which emulate human behavior, have achieved notable progress but overlook two critical aspects: 1) the integration of physical knowledge into models. Humans gain physical insights by observing the world and apply this knowledge to accurately reason about various dynamic scenarios; 2) the validation of model adaptability across diverse scenarios. Real-world dynamics, especially those involving fluids and objects, demand models that not only capture object interactions but also simulate fluid flow characteristics. To address these gaps, we introduce SlotPi, a slot-based physics-informed object-centric reasoning model. SlotPi integrates a physical module based on Hamiltonian principles with a spatio-temporal prediction module for dynamic forecasting. Our experiments highlight the model's strengths in tasks such as prediction and Visual Question Answering (VQA) on benchmark and fluid datasets. Furthermore, we have created a real-world dataset encompassing object interactions, fluid dynamics, and fluid-object interactions, on which we validated our model's capabilities. The model's robust performance across all datasets underscores its strong adaptability, laying a foundation for developing more advanced world models. △ Less

Submitted 12 June, 2025; originally announced June 2025.

IDCloak: A Practical Secure Multi-party Dataset Join Framework for Vertical Privacy-preserving Machine Learning

Authors: Shuyu Chen, Guopeng Lin, Haoyu Niu, Lushan Song, Chengxun Hong, Weili Han

Abstract: Vertical privacy-preserving machine learning (vPPML) enables multiple parties to train models on their vertically distributed datasets while keeping datasets private. In vPPML, it is critical to perform the secure dataset join, which aligns features corresponding to intersection IDs across datasets and forms a secret-shared and joint training dataset. However, existing methods for this step could… ▽ More Vertical privacy-preserving machine learning (vPPML) enables multiple parties to train models on their vertically distributed datasets while keeping datasets private. In vPPML, it is critical to perform the secure dataset join, which aligns features corresponding to intersection IDs across datasets and forms a secret-shared and joint training dataset. However, existing methods for this step could be impractical due to: (1) they are insecure when they expose intersection IDs; or (2) they rely on a strong trust assumption requiring a non-colluding auxiliary server; or (3) they are limited to the two-party setting. This paper proposes IDCloak, the first practical secure multi-party dataset join framework for vPPML that keeps IDs private without a non-colluding auxiliary server. IDCloak consists of two protocols: (1) a circuit-based multi-party private set intersection protocol (cmPSI), which obtains secret-shared flags indicating intersection IDs via an optimized communication structure combining OKVS and OPRF; (2) a secure multi-party feature alignment protocol, which obtains the secret-shared and joint dataset using secret-shared flags, via our proposed efficient secure shuffle protocol. Experiments show that: (1) compared to the state-of-the-art secure two-party dataset join framework (iPrivjoin), IDCloak demonstrates higher efficiency in the two-party setting and comparable performance when the party number increases; (2) compared to the state-of-the-art cmPSI protocol under honest majority, our proposed cmPSI protocol provides a stronger security guarantee (dishonest majority) while improving efficiency by up to $7.78\times$ in time and $8.73\times$ in communication sizes; (3) our proposed secure shuffle protocol outperforms the state-of-the-art shuffle protocol by up to $138.34\times$ in time and $132.13\times$ in communication sizes. △ Less

Submitted 1 June, 2025; originally announced June 2025.

Cognitively-Inspired Emergent Communication via Knowledge Graphs for Assisting the Visually Impaired

Authors: Ruxiao Chen, Dezheng Han, Wenjie Han, Shuaishuai Guo

Abstract: Assistive systems for visually impaired individuals must deliver rapid, interpretable, and adaptive feedback to facilitate real-time navigation. Current approaches face a trade-off between latency and semantic richness: natural language-based systems provide detailed guidance but are too slow for dynamic scenarios, while emergent communication frameworks offer low-latency symbolic languages but la… ▽ More Assistive systems for visually impaired individuals must deliver rapid, interpretable, and adaptive feedback to facilitate real-time navigation. Current approaches face a trade-off between latency and semantic richness: natural language-based systems provide detailed guidance but are too slow for dynamic scenarios, while emergent communication frameworks offer low-latency symbolic languages but lack semantic depth, limiting their utility in tactile modalities like vibration. To address these limitations, we introduce a novel framework, Cognitively-Inspired Emergent Communication via Knowledge Graphs (VAG-EC), which emulates human visual perception and cognitive mapping. Our method constructs knowledge graphs to represent objects and their relationships, incorporating attention mechanisms to prioritize task-relevant entities, thereby mirroring human selective attention. This structured approach enables the emergence of compact, interpretable, and context-sensitive symbolic languages. Extensive experiments across varying vocabulary sizes and message lengths demonstrate that VAG-EC outperforms traditional emergent communication methods in Topographic Similarity (TopSim) and Context Independence (CI). These findings underscore the potential of cognitively grounded emergent communication as a fast, adaptive, and human-aligned solution for real-time assistive technologies. Code is available at https://github.com/Anonymous-NLPcode/Anonymous_submission/tree/main. △ Less

Submitted 28 May, 2025; originally announced May 2025.

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research

Authors: Hui Chen, Miao Xiong, Yujie Lu, Wei Han, Ailin Deng, Yufei He, Jiaying Wu, Yibo Li, Yue Liu, Bryan Hooi

Abstract: Recent advancements in AI agents have demonstrated their growing potential to drive and support scientific discovery. In this work, we introduce MLR-Bench, a comprehensive benchmark for evaluating AI agents on open-ended machine learning research. MLR-Bench includes three key components: (1) 201 research tasks sourced from NeurIPS, ICLR, and ICML workshops covering diverse ML topics; (2) MLR-Judge… ▽ More Recent advancements in AI agents have demonstrated their growing potential to drive and support scientific discovery. In this work, we introduce MLR-Bench, a comprehensive benchmark for evaluating AI agents on open-ended machine learning research. MLR-Bench includes three key components: (1) 201 research tasks sourced from NeurIPS, ICLR, and ICML workshops covering diverse ML topics; (2) MLR-Judge, an automated evaluation framework combining LLM-based reviewers with carefully designed review rubrics to assess research quality; and (3) MLR-Agent, a modular agent scaffold capable of completing research tasks through four stages: idea generation, proposal formulation, experimentation, and paper writing. Our framework supports both stepwise assessment across these distinct research stages, and end-to-end evaluation of the final research paper. We then use MLR-Bench to evaluate six frontier LLMs and an advanced coding agent, finding that while LLMs are effective at generating coherent ideas and well-structured papers, current coding agents frequently (e.g., in 80% of the cases) produce fabricated or invalidated experimental results--posing a major barrier to scientific reliability. We validate MLR-Judge through human evaluation, showing high agreement with expert reviewers, supporting its potential as a scalable tool for research evaluation. We open-source MLR-Bench to help the community benchmark, diagnose, and improve AI research agents toward trustworthy and transparent scientific discovery. △ Less

Submitted 1 July, 2025; v1 submitted 26 May, 2025; originally announced May 2025.

Comments: 42 pages, 9 figures

Uncertainty-Aware Safety-Critical Decision and Control for Autonomous Vehicles at Unsignalized Intersections

Authors: Ran Yu, Zhuoren Li, Lu Xiong, Wei Han, Bo Leng

Abstract: Reinforcement learning (RL) has demonstrated potential in autonomous driving (AD) decision tasks. However, applying RL to urban AD, particularly in intersection scenarios, still faces significant challenges. The lack of safety constraints makes RL vulnerable to risks. Additionally, cognitive limitations and environmental randomness can lead to unreliable decisions in safety-critical scenarios. The… ▽ More Reinforcement learning (RL) has demonstrated potential in autonomous driving (AD) decision tasks. However, applying RL to urban AD, particularly in intersection scenarios, still faces significant challenges. The lack of safety constraints makes RL vulnerable to risks. Additionally, cognitive limitations and environmental randomness can lead to unreliable decisions in safety-critical scenarios. Therefore, it is essential to quantify confidence in RL decisions to improve safety. This paper proposes an Uncertainty-aware Safety-Critical Decision and Control (USDC) framework, which generates a risk-averse policy by constructing a risk-aware ensemble distributional RL, while estimating uncertainty to quantify the policy's reliability. Subsequently, a high-order control barrier function (HOCBF) is employed as a safety filter to minimize intervention policy while dynamically enhancing constraints based on uncertainty. The ensemble critics evaluate both HOCBF and RL policies, embedding uncertainty to achieve dynamic switching between safe and flexible strategies, thereby balancing safety and efficiency. Simulation tests on unsignalized intersections in multiple tasks indicate that USDC can improve safety while maintaining traffic efficiency compared to baselines. △ Less

Submitted 14 July, 2025; v1 submitted 26 May, 2025; originally announced May 2025.

Comments: 7 pages, 4 figures

Behavior Injection: Preparing Language Models for Reinforcement Learning

Authors: Zhepeng Cen, Yihang Yao, William Han, Zuxin Liu, Ding Zhao

Abstract: Reinforcement fine-tuning (RFT) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RFT: some show substantial performance gains, while others plateau or even degrade. To understand this divergence, we analyze the per-step influence of the RL objective and identify two key condition… ▽ More Reinforcement fine-tuning (RFT) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RFT: some show substantial performance gains, while others plateau or even degrade. To understand this divergence, we analyze the per-step influence of the RL objective and identify two key conditions for effective post-training: (1) RL-informative rollout accuracy, and (2) strong data co-influence, which quantifies how much the training data affects performance on other samples. Guided by these insights, we propose behavior injection, a task-agnostic data-augmentation scheme applied prior to RL. Behavior injection enriches the supervised finetuning (SFT) data by seeding exploratory and exploitative behaviors, effectively making the model more RL-ready. We evaluate our method across two reasoning benchmarks with multiple base models. The results demonstrate that our theoretically motivated augmentation can significantly increases the performance gain from RFT over the pre-RL model. △ Less

Submitted 24 May, 2025; originally announced May 2025.

Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework

Authors: William Han, Chaojing Duan, Zhepeng Cen, Yihang Yao, Xiaoyu Song, Atharva Mhaskar, Dylan Leong, Michael A. Rosenberg, Emerson Liu, Ding Zhao

Abstract: Recent advances have increasingly applied large language models (LLMs) to electrocardiogram (ECG) interpretation, giving rise to Electrocardiogram-Language Models (ELMs). Conditioned on an ECG and a textual query, an ELM autoregressively generates a free-form textual response. Unlike traditional classification-based systems, ELMs emulate expert cardiac electrophysiologists by issuing diagnoses, an… ▽ More Recent advances have increasingly applied large language models (LLMs) to electrocardiogram (ECG) interpretation, giving rise to Electrocardiogram-Language Models (ELMs). Conditioned on an ECG and a textual query, an ELM autoregressively generates a free-form textual response. Unlike traditional classification-based systems, ELMs emulate expert cardiac electrophysiologists by issuing diagnoses, analyzing waveform morphology, identifying contributing factors, and proposing patient-specific action plans. To realize this potential, researchers are curating instruction-tuning datasets that pair ECGs with textual dialogues and are training ELMs on these resources. Yet before scaling ELMs further, there is a fundamental question yet to be explored: What is the most effective ECG input representation? In recent works, three candidate representations have emerged-raw time-series signals, rendered images, and discretized symbolic sequences. We present the first comprehensive benchmark of these modalities across 6 public datasets and 5 evaluation metrics. We find symbolic representations achieve the greatest number of statistically significant wins over both signal and image inputs. We further ablate the LLM backbone, ECG duration, and token budget, and we evaluate robustness to signal perturbations. We hope that our findings offer clear guidance for selecting input representations when developing the next generation of ELMs. △ Less

Submitted 24 May, 2025; originally announced May 2025.

Comments: 29 pages, 2 figures, 8 tables

RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning

Authors: Mingrui Wu, Lu Wang, Pu Zhao, Fangkai Yang, Jianjin Zhang, Jianfeng Liu, Yuefeng Zhan, Weihao Han, Hao Sun, Jiayi Ji, Xiaoshuai Sun, Qingwei Lin, Weiwei Deng, Dongmei Zhang, Feng Sun, Qi Zhang, Rongrong Ji

Abstract: Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language models (LLMs), these methods frequently generate stylistic or unrealistic content due to insufficient grounding in visual semantics and real-world composition. I… ▽ More Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language models (LLMs), these methods frequently generate stylistic or unrealistic content due to insufficient grounding in visual semantics and real-world composition. Inspired by recent advances in reasoning for language model, we propose RePrompt, a novel reprompting framework that introduces explicit reasoning into the prompt enhancement process via reinforcement learning. Instead of relying on handcrafted rules or stylistic rewrites, our method trains a language model to generate structured, self-reflective prompts by optimizing for image-level outcomes. The tailored reward models assesse the generated images in terms of human preference, semantic alignment, and visual composition, providing indirect supervision to refine prompt generation. Our approach enables end-to-end training without human-annotated data. Experiments on GenEval and T2I-Compbench show that RePrompt significantly boosts spatial layout fidelity and compositional generalization across diverse T2I backbones, establishing new state-of-the-art results. △ Less

Submitted 23 May, 2025; originally announced May 2025.

Comments: Code is available at: https://github.com/microsoft/DKI_LLM/tree/main/RePrompt

Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation

Authors: Hongji Yang, Yucheng Zhou, Wencheng Han, Jianbing Shen

Abstract: Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision from large amounts of manually annotated data and trained aesthetic assessment models. To alleviate the dependence on data scale for model training and the biases… ▽ More Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision from large amounts of manually annotated data and trained aesthetic assessment models. To alleviate the dependence on data scale for model training and the biases introduced by trained models, we propose a novel prompt optimization framework, designed to rephrase a simple user prompt into a sophisticated prompt to a text-to-image model. Specifically, we employ the large vision language models (LVLMs) as the solver to rewrite the user prompt, and concurrently, employ LVLMs as a reward model to score the aesthetics and alignment of the images generated by the optimized prompt. Instead of laborious human feedback, we exploit the prior knowledge of the LVLM to provide rewards, i.e., AI feedback. Simultaneously, the solver and the reward model are unified into one model and iterated in reinforcement learning to achieve self-improvement by giving a solution and judging itself. Results on two popular datasets demonstrate that our method outperforms other strong competitors. △ Less

Submitted 22 May, 2025; originally announced May 2025.

Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting

Authors: Youngmoon Jung, Yong-Hyeok Lee, Myunghun Jung, Jaeyoung Roh, Chang Woo Han, Hoon-Young Cho

Abstract: For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this, we optimize acoustic and text encoders using deep metric learning (DML), enabling direct comparison of multi-modal embeddings in a shared embedding space. However, the inherent heterogeneity between audio and text modali… ▽ More For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this, we optimize acoustic and text encoders using deep metric learning (DML), enabling direct comparison of multi-modal embeddings in a shared embedding space. However, the inherent heterogeneity between audio and text modalities presents a significant challenge. To address this, we propose Modality Adversarial Learning (MAL), which reduces the domain gap in heterogeneous modality representations. Specifically, we train a modality classifier adversarially to encourage both encoders to generate modality-invariant embeddings. Additionally, we apply DML to achieve phoneme-level alignment between audio and text, and conduct extensive comparisons across various DML objectives. Experiments on the Wall Street Journal (WSJ) and LibriPhrase datasets demonstrate the effectiveness of the proposed approach. △ Less

Submitted 22 May, 2025; v1 submitted 22 May, 2025; originally announced May 2025.

Comments: 5 pages, 1 figure, Accepted at Interspeech 2025

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought

Authors: Tencent Hunyuan Team, Ao Liu, Botong Zhou, Can Xu, Chayse Zhou, ChenChen Zhang, Chengcheng Xu, Chenhao Wang, Decheng Wu, Dengpeng Wu, Dian Jiao, Dong Du, Dong Wang, Feng Zhang, Fengzong Lian, Guanghui Xu, Guanwei Zhang, Hai Wang, Haipeng Luo, Han Hu, Huilin Xu, Jiajia Wu, Jianchen Zhu, Jianfeng Yan, Jiaqi Zhu , et al. (230 additional authors not shown)

Abstract: As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching between rapid response… ▽ More As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching between rapid responses for simple queries and deep "thinking" modes for complex problems, optimizing computational resources. Architecturally, this 56B activated (560B total) parameter model employs 128 layers (Mamba2, Attention, FFN) with an innovative AMF/MF block pattern. Faster Mamba2 ensures linear complexity, Grouped-Query Attention minimizes KV cache, and FFNs use an MoE structure. Pre-trained on 16T high-quality tokens, it supports a 256K context length and is the first industry-deployed large-scale Mamba model. Our comprehensive post-training strategy enhances capabilities via Supervised Fine-Tuning (3M instructions), a novel Adaptive Long-short CoT Fusion method, Multi-round Deliberation Learning for iterative improvement, and a two-stage Large-scale Reinforcement Learning process targeting STEM and general instruction-following. Evaluations show strong performance: overall top 7 rank on LMSYS Chatbot Arena with a score of 1356, outperforming leading models like Gemini-2.0-Flash-001 (1352) and o4-mini-2025-04-16 (1345). TurboS also achieves an average of 77.9% across 23 automated benchmarks. Hunyuan-TurboS balances high performance and efficiency, offering substantial capabilities at lower inference costs than many reasoning models, establishing a new paradigm for efficient large-scale pre-trained models. △ Less

Submitted 4 July, 2025; v1 submitted 21 May, 2025; originally announced May 2025.

Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer

Authors: Wenkang Han, Wang Lin, Liya Hu, Zhenlong Dai, Yiyun Zhou, Mengze Li, Zemin Liu, Chang Yao, Jingyuan Chen

Abstract: Knowledge tracing (KT) aims to predict learners' future performance based on historical learning interactions. However, existing KT models predominantly focus on data from a single course, limiting their ability to capture a comprehensive understanding of learners' knowledge states. In this paper, we propose TransKT, a contrastive cross-course knowledge tracing method that leverages concept graph… ▽ More Knowledge tracing (KT) aims to predict learners' future performance based on historical learning interactions. However, existing KT models predominantly focus on data from a single course, limiting their ability to capture a comprehensive understanding of learners' knowledge states. In this paper, we propose TransKT, a contrastive cross-course knowledge tracing method that leverages concept graph guided knowledge transfer to model the relationships between learning behaviors across different courses, thereby enhancing knowledge state estimation. Specifically, TransKT constructs a cross-course concept graph by leveraging zero-shot Large Language Model (LLM) prompts to establish implicit links between related concepts across different courses. This graph serves as the foundation for knowledge transfer, enabling the model to integrate and enhance the semantic features of learners' interactions across courses. Furthermore, TransKT includes an LLM-to-LM pipeline for incorporating summarized semantic features, which significantly improves the performance of Graph Convolutional Networks (GCNs) used for knowledge transfer. Additionally, TransKT employs a contrastive objective that aligns single-course and cross-course knowledge states, thereby refining the model's ability to provide a more robust and accurate representation of learners' overall knowledge states. △ Less

Submitted 14 May, 2025; originally announced May 2025.

Comments: Accepted by IJCAI 2025

GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation

Authors: Abhay Deshpande, Yuquan Deng, Arijit Ray, Jordi Salvador, Winson Han, Jiafei Duan, Kuo-Hao Zeng, Yuke Zhu, Ranjay Krishna, Rose Hendrix

Abstract: We present GrasMolmo, a generalizable open-vocabulary task-oriented grasping (TOG) model. GraspMolmo predicts semantically appropriate, stable grasps conditioned on a natural language instruction and a single RGB-D frame. For instance, given "pour me some tea", GraspMolmo selects a grasp on a teapot handle rather than its body. Unlike prior TOG methods, which are limited by small datasets, simplis… ▽ More We present GrasMolmo, a generalizable open-vocabulary task-oriented grasping (TOG) model. GraspMolmo predicts semantically appropriate, stable grasps conditioned on a natural language instruction and a single RGB-D frame. For instance, given "pour me some tea", GraspMolmo selects a grasp on a teapot handle rather than its body. Unlike prior TOG methods, which are limited by small datasets, simplistic language, and uncluttered scenes, GraspMolmo learns from PRISM, a novel large-scale synthetic dataset of 379k samples featuring cluttered environments and diverse, realistic task descriptions. We fine-tune the Molmo visual-language model on this data, enabling GraspMolmo to generalize to novel open-vocabulary instructions and objects. In challenging real-world evaluations, GraspMolmo achieves state-of-the-art results, with a 70% prediction success on complex tasks, compared to the 35% achieved by the next best alternative. GraspMolmo also successfully demonstrates the ability to predict semantically correct bimanual grasps zero-shot. We release our synthetic dataset, code, model, and benchmarks to accelerate research in task-semantic robotic manipulation, which, along with videos, are available at https://abhaybd.github.io/GraspMolmo/. △ Less

Submitted 22 May, 2025; v1 submitted 19 May, 2025; originally announced May 2025.

PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning

Authors: Yeonkyung Lee, Woojung Han, Youngjun Jun, Hyeonmin Kim, Jungkyung Cho, Seong Jae Hwang

Abstract: Retinal foundation models have significantly advanced retinal image analysis by leveraging self-supervised learning to reduce dependence on labeled data while achieving strong generalization. Many recent approaches enhance retinal image understanding using report supervision, but obtaining clinical reports is often costly and challenging. In contrast, metadata (e.g., age, gender) is widely availab… ▽ More Retinal foundation models have significantly advanced retinal image analysis by leveraging self-supervised learning to reduce dependence on labeled data while achieving strong generalization. Many recent approaches enhance retinal image understanding using report supervision, but obtaining clinical reports is often costly and challenging. In contrast, metadata (e.g., age, gender) is widely available and serves as a valuable resource for analyzing disease progression. To effectively incorporate patient-specific information, we propose PRETI, a retinal foundation model that integrates metadata-aware learning with robust self-supervised representation learning. We introduce Learnable Metadata Embedding (LME), which dynamically refines metadata representations. Additionally, we construct patient-level data pairs, associating images from the same individual to improve robustness against non-clinical variations. To further optimize retinal image representation, we propose Retina-Aware Adaptive Masking (RAAM), a strategy that selectively applies masking within the retinal region and dynamically adjusts the masking ratio during training. PRETI captures both global structures and fine-grained pathological details, resulting in superior diagnostic performance. Extensive experiments demonstrate that PRETI achieves state-of-the-art results across diverse diseases and biomarker predictions using in-house and public data, indicating the importance of metadata-guided foundation models in retinal disease analysis. Our code and pretrained model are available at https://github.com/MICV-yonsei/PRETI △ Less

Submitted 18 May, 2025; originally announced May 2025.

Comments: MICCAI2025 early accept

On the Account Security Risks Posed by Password Strength Meters

Authors: Ming Xu, Weili Han, Jitao Yu, Jing Liu, Xinyi Zhang, Yun Lin, Jin Song Dong

Abstract: Password strength meters (PSMs) have been widely used by websites to gauge password strength, encouraging users to create stronger passwords. Popular data-driven PSMs, e.g., based on Markov, Probabilistic Context-free Grammar (PCFG) and neural networks, alarm strength based on a model learned from real passwords. Despite their proven effectiveness, the secure utility that arises from the leakage o… ▽ More Password strength meters (PSMs) have been widely used by websites to gauge password strength, encouraging users to create stronger passwords. Popular data-driven PSMs, e.g., based on Markov, Probabilistic Context-free Grammar (PCFG) and neural networks, alarm strength based on a model learned from real passwords. Despite their proven effectiveness, the secure utility that arises from the leakage of trained passwords remains largely overlooked. To address this gap, we analyze 11 PSMs and find that 5 data-driven meters are vulnerable to membership inference attacks that expose their trained passwords, and seriously, 3 rule-based meters openly disclose their blocked passwords. We specifically design a PSM privacy leakage evaluation approach, and uncover that a series of general data-driven meters are vulnerable to leaking between 10^4 to 10^5 trained passwords, with the PCFG-based models being more vulnerable than other counterparts; furthermore, we aid in deriving insights that the inherent utility-privacy tradeoff is not as severe as previously thought. To further exploit the risks, we develop novel meter-aware attacks when a clever attacker can filter the used passwords during compromising accounts on websites using the meter, and experimentally show that attackers targeting websites that deployed the popular Zxcvbn meter can compromise an additional 5.84% user accounts within 10 attempts, demonstrating the urgent need for privacy-preserving PSMs that protect the confidentiality of the meter's used passwords. Finally, we sketch some counter-measures to mitigate these threats. △ Less

Submitted 13 May, 2025; originally announced May 2025.

Towards Better Cephalometric Landmark Detection with Diffusion Data Generation

Authors: Dongqian Guo, Wencheng Han, Pang Lyu, Yuxi Zhou, Jianbing Shen

Abstract: Cephalometric landmark detection is essential for orthodontic diagnostics and treatment planning. Nevertheless, the scarcity of samples in data collection and the extensive effort required for manual annotation have significantly impeded the availability of diverse datasets. This limitation has restricted the effectiveness of deep learning-based detection methods, particularly those based on large… ▽ More Cephalometric landmark detection is essential for orthodontic diagnostics and treatment planning. Nevertheless, the scarcity of samples in data collection and the extensive effort required for manual annotation have significantly impeded the availability of diverse datasets. This limitation has restricted the effectiveness of deep learning-based detection methods, particularly those based on large-scale vision models. To address these challenges, we have developed an innovative data generation method capable of producing diverse cephalometric X-ray images along with corresponding annotations without human intervention. To achieve this, our approach initiates by constructing new cephalometric landmark annotations using anatomical priors. Then, we employ a diffusion-based generator to create realistic X-ray images that correspond closely with these annotations. To achieve precise control in producing samples with different attributes, we introduce a novel prompt cephalometric X-ray image dataset. This dataset includes real cephalometric X-ray images and detailed medical text prompts describing the images. By leveraging these detailed prompts, our method improves the generation process to control different styles and attributes. Facilitated by the large, diverse generated data, we introduce large-scale vision detection models into the cephalometric landmark detection task to improve accuracy. Experimental results demonstrate that training with the generated data substantially enhances the performance. Compared to methods without using the generated data, our approach improves the Success Detection Rate (SDR) by 6.5%, attaining a notable 82.2%. All code and data are available at: https://um-lab.github.io/cepha-generation △ Less

Submitted 9 May, 2025; originally announced May 2025.

SToLa: Self-Adaptive Touch-Language Framework with Tactile Commonsense Reasoning in Open-Ended Scenarios

Authors: Ning Cheng, Jinan Xu, Jialing Chen, Wenjuan Han

Abstract: This paper explores the challenges of integrating tactile sensing into intelligent systems for multimodal reasoning, particularly in enabling commonsense reasoning about the open-ended physical world. We identify two key challenges: modality discrepancy, where existing large touch-language models often treat touch as a mere sub-modality of language, and open-ended tactile data scarcity, where curr… ▽ More This paper explores the challenges of integrating tactile sensing into intelligent systems for multimodal reasoning, particularly in enabling commonsense reasoning about the open-ended physical world. We identify two key challenges: modality discrepancy, where existing large touch-language models often treat touch as a mere sub-modality of language, and open-ended tactile data scarcity, where current datasets lack the diversity, open-endness and complexity needed for reasoning. To overcome these challenges, we introduce SToLa, a Self-Adaptive Touch-Language framework. SToLa utilizes Mixture of Experts (MoE) to dynamically process, unify, and manage tactile and language modalities, capturing their unique characteristics. Crucially, we also present a comprehensive tactile commonsense reasoning dataset and benchmark featuring free-form questions and responses, 8 physical properties, 4 interactive characteristics, and diverse commonsense knowledge. Experiments show SToLa exhibits competitive performance compared to existing models on the PhysiCLeAR benchmark and self-constructed datasets, proving the effectiveness of the Mixture of Experts architecture in multimodal management and the performance advantages for open-scenario tactile commonsense reasoning tasks. △ Less

Submitted 7 May, 2025; originally announced May 2025.

The Shift Towards Preprints in AI Policy Research: A Comparative Study of Preprint Trends in the U.S., Europe, and South Korea

Authors: Simon Suh, Jihyuk Bang, Ji Woo Han

Abstract: The adoption of open science has quickly changed how artificial intelligence (AI) policy research is distributed globally. This study examines the regional trends in the citation of preprints, specifically focusing on the impact of two major disruptive events: the COVID-19 pandemic and the release of ChatGPT, on research dissemination patterns in the United States, Europe, and South Korea from 201… ▽ More The adoption of open science has quickly changed how artificial intelligence (AI) policy research is distributed globally. This study examines the regional trends in the citation of preprints, specifically focusing on the impact of two major disruptive events: the COVID-19 pandemic and the release of ChatGPT, on research dissemination patterns in the United States, Europe, and South Korea from 2015 to 2024. Using bibliometrics data from the Web of Science, this study tracks how global disruptive events influenced the adoption of preprints in AI policy research and how such shifts vary by region. By marking the timing of these disruptive events, the analysis reveals that while all regions experienced growth in preprint citations, the magnitude and trajectory of change varied significantly. The United States exhibited sharp, event-driven increases; Europe demonstrated institutional growth; and South Korea maintained consistent, linear growth in preprint adoption. These findings suggest that global disruptions may have accelerated preprint adoption, but the extent and trajectory are shaped by local research cultures, policy environments, and levels of open science maturity. This paper emphasizes the need for future AI governance strategies to consider regional variability in research dissemination and highlights opportunities for further longitudinal and comparative research to deepen our understanding of open-access adoption in AI policy development. △ Less

Submitted 4 May, 2025; originally announced May 2025.

Comments: 22 pages, 6 figures, 3 tables. Uses cross-regional analysis to evaluate how preprint citation trends in AI - policy research have shifted over time in response to two major global events: the COVID-19 pandemic and the release of ChatGPT. Compares United States, Europe, and South Korea

ACM Class: I.2.0; K.4.0

PREMISE: Matching-based Prediction for Accurate Review Recommendation

Authors: Wei Han, Hui Chen, Soujanya Poria

Abstract: We present PREMISE (PREdict with Matching ScorEs), a new architecture for the matching-based learning in the multimodal fields for the multimodal review helpfulness (MRHP) task. Distinct to previous fusion-based methods which obtains multimodal representations via cross-modal attention for downstream tasks, PREMISE computes the multi-scale and multi-field representations, filters duplicated semant… ▽ More We present PREMISE (PREdict with Matching ScorEs), a new architecture for the matching-based learning in the multimodal fields for the multimodal review helpfulness (MRHP) task. Distinct to previous fusion-based methods which obtains multimodal representations via cross-modal attention for downstream tasks, PREMISE computes the multi-scale and multi-field representations, filters duplicated semantics, and then obtained a set of matching scores as feature vectors for the downstream recommendation task. This new architecture significantly boosts the performance for such multimodal tasks whose context matching content are highly correlated to the targets of that task, compared to the state-of-the-art fusion-based methods. Experimental results on two publicly available datasets show that PREMISE achieves promising performance with less computational cost. △ Less

Submitted 2 May, 2025; originally announced May 2025.

Comments: 19 pages, 16 figures

Enhancing Realism in Holographic Augmented Reality Displays through Occlusion Handling

Authors: Woongseob Han, Chanseul Lee, Jae-Hyeung Park

Abstract: In this paper, an occlusion-capable holographic augmented-reality (AR) display is proposed, and its ability to enhance AR imagery through occlusion is demonstrated. Holographic displays can generate ideal three-dimensional (3D) virtual images and have recently shown rapid advancements, particularly in noise reduction through learning-based approaches. However, these displays still face challenges… ▽ More In this paper, an occlusion-capable holographic augmented-reality (AR) display is proposed, and its ability to enhance AR imagery through occlusion is demonstrated. Holographic displays can generate ideal three-dimensional (3D) virtual images and have recently shown rapid advancements, particularly in noise reduction through learning-based approaches. However, these displays still face challenges in improving image quality for AR scenarios because holographic virtual images are simply superimposed onto the real world, leading to a loss of contrast and visibility. To address this, an occlusion optics, which can mask designated areas of the real world, is incorporated into holographic AR displays. The proposed system employs a folded 4f system with a digital micromirror device and sequentially operates as both a real-world mask and an active Fourier filter. This approach transforms traditionally translucent holographic images into perceptually opaque ones while simultaneously eliminating unwanted noise terms from pixelated holographic displays. Furthermore, active Fourier filtering expands the virtual image field of view through time-multiplexed operation and supports a novel binary hologram optimization algorithm that performs especially well for sparse virtual content. The implementation successfully achieves opaque holographic 3D image presentation, significantly improving contrast and image quality while producing highly realistic 3D AR scenes with optically cast shadows. △ Less

Submitted 1 May, 2025; originally announced May 2025.

Comments: 24 pages, 10 figures

ScaleTrack: Scaling and back-tracking Automated GUI Agents

Authors: Jing Huang, Zhixiong Zeng, Wenkang Han, Yufeng Zhong, Liming Zheng, Shuai Fu, Jingyuan Chen, Lin Ma

Abstract: Automated GUI agents aims to facilitate user interaction by automatically performing complex tasks in digital environments, such as web, mobile, desktop devices. It receives textual task instruction and GUI description to generate executable actions (\emph{e.g.}, click) and operation boxes step by step. Training a GUI agent mainly involves grounding and planning stages, in which the GUI grounding… ▽ More Automated GUI agents aims to facilitate user interaction by automatically performing complex tasks in digital environments, such as web, mobile, desktop devices. It receives textual task instruction and GUI description to generate executable actions (\emph{e.g.}, click) and operation boxes step by step. Training a GUI agent mainly involves grounding and planning stages, in which the GUI grounding focuses on finding the execution coordinates according to the task, while the planning stage aims to predict the next action based on historical actions. However, previous work suffers from the limitations of insufficient training data for GUI grounding, as well as the ignorance of backtracking historical behaviors for GUI planning. To handle the above challenges, we propose ScaleTrack, a training framework by scaling grounding and backtracking planning for automated GUI agents. We carefully collected GUI samples of different synthesis criterions from a wide range of sources, and unified them into the same template for training GUI grounding models. Moreover, we design a novel training strategy that predicts the next action from the current GUI image, while also backtracking the historical actions that led to the GUI image. In this way, ScaleTrack explains the correspondence between GUI images and actions, which effectively describes the evolution rules of the GUI environment. Extensive experimental results demonstrate the effectiveness of ScaleTrack. Data and code will be available at url. △ Less

Submitted 1 May, 2025; originally announced May 2025.

ReCellTy: Domain-specific knowledge graph retrieval-augmented LLMs workflow for single-cell annotation

Authors: Dezheng Han, Yibin Jia, Ruxiao Chen, Wenjie Han, Shuaishuai Guo, Jianbo Wang

Abstract: To enable precise and fully automated cell type annotation with large language models (LLMs), we developed a graph structured feature marker database to retrieve entities linked to differential genes for cell reconstruction. We further designed a multi task workflow to optimize the annotation process. Compared to general purpose LLMs, our method improves human evaluation scores by up to 0.21 and s… ▽ More To enable precise and fully automated cell type annotation with large language models (LLMs), we developed a graph structured feature marker database to retrieve entities linked to differential genes for cell reconstruction. We further designed a multi task workflow to optimize the annotation process. Compared to general purpose LLMs, our method improves human evaluation scores by up to 0.21 and semantic similarity by 6.1% across 11 tissue types, while more closely aligning with the cognitive logic of manual annotation. △ Less

Submitted 23 April, 2025; originally announced May 2025.

Geometry-aware Temporal Aggregation Network for Monocular 3D Lane Detection

Authors: Huan Zheng, Wencheng Han, Tianyi Yan, Cheng-zhong Xu, Jianbing Shen

Abstract: Monocular 3D lane detection aims to estimate 3D position of lanes from frontal-view (FV) images. However, current monocular 3D lane detection methods suffer from two limitations, including inaccurate geometric information of the predicted 3D lanes and difficulties in maintaining lane integrity. To address these issues, we seek to fully exploit the potential of multiple input frames. First, we aim… ▽ More Monocular 3D lane detection aims to estimate 3D position of lanes from frontal-view (FV) images. However, current monocular 3D lane detection methods suffer from two limitations, including inaccurate geometric information of the predicted 3D lanes and difficulties in maintaining lane integrity. To address these issues, we seek to fully exploit the potential of multiple input frames. First, we aim at enhancing the ability to perceive the geometry of scenes by leveraging temporal geometric consistency. Second, we strive to improve the integrity of lanes by revealing more instance information from temporal sequences. Therefore, we propose a novel Geometry-aware Temporal Aggregation Network (GTA-Net) for monocular 3D lane detection. On one hand, we develop the Temporal Geometry Enhancement Module (TGEM), which exploits geometric consistency across successive frames, facilitating effective geometry perception. On the other hand, we present the Temporal Instance-aware Query Generation (TIQG), which strategically incorporates temporal cues into query generation, thereby enabling the exploration of comprehensive instance information. Experiments demonstrate that our GTA-Net achieves SoTA results, surpassing existing monocular 3D lane detection solutions. △ Less

Submitted 29 April, 2025; originally announced April 2025.

ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources

Authors: Yikuan Xia, Jiazun Chen, Yirui Zhan, Suifeng Zhao, Weipeng Jiang, Chaorui Zhang, Wei Han, Bo Bai, Jun Gao

Abstract: Large language models (LLMs) excel in question-answering (QA) tasks, and retrieval-augmented generation (RAG) enhances their precision by incorporating external evidence from diverse sources like web pages, databases, and knowledge graphs. However, current RAG methods rely on agent-specific strategies for individual data sources, posing challenges low-resource or black-box environments and complic… ▽ More Large language models (LLMs) excel in question-answering (QA) tasks, and retrieval-augmented generation (RAG) enhances their precision by incorporating external evidence from diverse sources like web pages, databases, and knowledge graphs. However, current RAG methods rely on agent-specific strategies for individual data sources, posing challenges low-resource or black-box environments and complicates operations when evidence is fragmented across sources. To address these limitations, we propose ER-RAG, a framework that unifies evidence integration across heterogeneous data sources using the Entity-Relationship (ER) model. ER-RAG standardizes entity retrieval and relationship querying through ER-based APIs with GET and JOIN operations. It employs a two-stage generation process: first, a preference optimization module selects optimal sources; second, another module constructs API chains based on source schemas. This unified approach allows efficient fine-tuning and seamless integration across diverse data sources. ER-RAG demonstrated its effectiveness by winning all three tracks of the 2024 KDDCup CRAG Challenge, achieving performance on par with commercial RAG pipelines using an 8B LLM backbone. It outperformed hybrid competitors by 3.1% in LLM score and accelerated retrieval by 5.5X. △ Less

Submitted 2 March, 2025; originally announced April 2025.

APSeg: Auto-Prompt Model with Acquired and Injected Knowledge for Nuclear Instance Segmentation and Classification

Authors: Liying Xu, Hongliang He, Wei Han, Hanbin Huang, Siwei Feng, Guohong Fu

Abstract: Nuclear instance segmentation and classification provide critical quantitative foundations for digital pathology diagnosis. With the advent of the foundational Segment Anything Model (SAM), the accuracy and efficiency of nuclear segmentation have improved significantly. However, SAM imposes a strong reliance on precise prompts, and its class-agnostic design renders its classification results entir… ▽ More Nuclear instance segmentation and classification provide critical quantitative foundations for digital pathology diagnosis. With the advent of the foundational Segment Anything Model (SAM), the accuracy and efficiency of nuclear segmentation have improved significantly. However, SAM imposes a strong reliance on precise prompts, and its class-agnostic design renders its classification results entirely dependent on the provided prompts. Therefore, we focus on generating prompts with more accurate localization and classification and propose \textbf{APSeg}, \textbf{A}uto-\textbf{P}rompt model with acquired and injected knowledge for nuclear instance \textbf{Seg}mentation and classification. APSeg incorporates two knowledge-aware modules: (1) Distribution-Guided Proposal Offset Module (\textbf{DG-POM}), which learns distribution knowledge through density map guided, and (2) Category Knowledge Semantic Injection Module (\textbf{CK-SIM}), which injects morphological knowledge derived from category descriptions. We conducted extensive experiments on the PanNuke and CoNSeP datasets, demonstrating the effectiveness of our approach. The code will be released upon acceptance. △ Less

Submitted 2 April, 2025; originally announced April 2025.

Comments: 10 pages, 3 figures

TransMamba: Flexibly Switching between Transformer and Mamba

Authors: Yixing Li, Ruobing Xie, Zhen Yang, Xingwu Sun, Shuaipeng Li, Weidong Han, Zhanhui Kang, Yu Cheng, Chengzhong Xu, Di Wang, Jie Jiang

Abstract: Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in long-sequence processing. Recent advancements in Mamba, a state space model (SSM) with linear complexity, offer promising efficiency gains but suffer from unstable contextual learning and multitask generalization. This paper proposes TransMamba, a novel framework that… ▽ More Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in long-sequence processing. Recent advancements in Mamba, a state space model (SSM) with linear complexity, offer promising efficiency gains but suffer from unstable contextual learning and multitask generalization. This paper proposes TransMamba, a novel framework that unifies Transformer and Mamba through shared parameter matrices (e.g., QKV and CBx), and thus could dynamically switch between attention and SSM mechanisms at different token lengths and layers. We design the Memory converter to bridge Transformer and Mamba by converting attention outputs into SSM-compatible states, ensuring seamless information flow at TransPoints where the transformation happens. The TransPoint scheduling is also thoroughly explored for further improvements. We conducted extensive experiments demonstrating that TransMamba achieves superior training efficiency and performance compared to baselines, and validated the deeper consistency between Transformer and Mamba paradigms, offering a scalable solution for next-generation sequence modeling. △ Less

Submitted 31 March, 2025; originally announced March 2025.

Comments: Preprint. Under review

A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective

Authors: Zhuoren Li, Guizhe Jin, Ran Yu, Zhiwen Chen, Nan Li, Wei Han, Lu Xiong, Bo Leng, Jia Hu, Ilya Kolmanovsky, Dimitar Filev

Abstract: Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD). Despite rapid advancements in RL and AD, a systematic description and interpretation of the RL design process tailored to diverse driving tasks remains underdeveloped.… ▽ More Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD). Despite rapid advancements in RL and AD, a systematic description and interpretation of the RL design process tailored to diverse driving tasks remains underdeveloped. This survey provides a comprehensive review of RL-based MoP for AD, focusing on lessons from task-specific perspectives. We first outline the fundamentals of RL methodologies, and then survey their applications in MoP, analyzing scenario-specific features and task requirements to shed light on their influence on RL design choices. Building on this analysis, we summarize key design experiences, extract insights from various driving task applications, and provide guidance for future implementations. Additionally, we examine the frontier challenges in RL-based MoP, review recent efforts to addresse these challenges, and propose strategies for overcoming unresolved issues. △ Less

Submitted 30 March, 2025; originally announced March 2025.

Comments: 21 pages, 5 figures

Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis

Authors: Woojung Han, Yeonkyung Lee, Chanyoung Kim, Kwanghyun Park, Seong Jae Hwang

Abstract: Diffusion-based text-to-image (T2I) models have recently excelled in high-quality image generation, particularly in a training-free manner, enabling cost-effective adaptability and generalization across diverse tasks. However, while the existing methods have been continuously focusing on several challenges, such as "missing objects" and "mismatched attributes," another critical issue of "mislocate… ▽ More Diffusion-based text-to-image (T2I) models have recently excelled in high-quality image generation, particularly in a training-free manner, enabling cost-effective adaptability and generalization across diverse tasks. However, while the existing methods have been continuously focusing on several challenges, such as "missing objects" and "mismatched attributes," another critical issue of "mislocated objects" remains where generated spatial positions fail to align with text prompts. Surprisingly, ensuring such seemingly basic functionality remains challenging in popular T2I models due to the inherent difficulty of imposing explicit spatial guidance via text forms. To address this, we propose STORM (Spatial Transport Optimization by Repositioning Attention Map), a novel training-free approach for spatially coherent T2I synthesis. STORM employs Spatial Transport Optimization (STO), rooted in optimal transport theory, to dynamically adjust object attention maps for precise spatial adherence, supported by a Spatial Transport (ST) Cost function that enhances spatial understanding. Our analysis shows that integrating spatial awareness is most effective in the early denoising stages, while later phases refine details. Extensive experiments demonstrate that STORM surpasses existing methods, effectively mitigating mislocated objects while improving missing and mismatched attributes, setting a new benchmark for spatial alignment in T2I synthesis. △ Less

Submitted 28 March, 2025; originally announced March 2025.

Comments: CVPR2025

Reducing CT Metal Artifacts by Learning Latent Space Alignment with Gemstone Spectral Imaging Data

Authors: Wencheng Han, Dongqian Guo, Xiao Chen, Pang Lyu, Yi Jin, Jianbing Shen

Abstract: Metal artifacts in CT slices have long posed challenges in medical diagnostics. These artifacts degrade image quality, resulting in suboptimal visualization and complicating the accurate interpretation of tissues adjacent to metal implants. To address these issues, we introduce the Latent Gemstone Spectral Imaging (GSI) Alignment Framework, which effectively reduces metal artifacts while avoiding… ▽ More Metal artifacts in CT slices have long posed challenges in medical diagnostics. These artifacts degrade image quality, resulting in suboptimal visualization and complicating the accurate interpretation of tissues adjacent to metal implants. To address these issues, we introduce the Latent Gemstone Spectral Imaging (GSI) Alignment Framework, which effectively reduces metal artifacts while avoiding the introduction of noise information. Our work is based on a key finding that even artifact-affected ordinary CT sequences contain sufficient information to discern detailed structures. The challenge lies in the inability to clearly represent this information. To address this issue, we developed an Alignment Framework that adjusts the representation of ordinary CT images to match GSI CT sequences. GSI is an advanced imaging technique using multiple energy levels to mitigate artifacts caused by metal implants. By aligning the representation to GSI data, we can effectively suppress metal artifacts while clearly revealing detailed structure, without introducing extraneous information into CT sequences. To facilitate the application, we propose a new dataset, Artifacts-GSI, captured from real patients with metal implants, and establish a new benchmark based on this dataset. Experimental results show that our method significantly reduces metal artifacts and greatly enhances the readability of CT slices. All our code and data are available at: https://um-lab.github.io/GSI-MAR/ △ Less

Submitted 27 March, 2025; originally announced March 2025.

Gemma 3 Technical Report

Authors: Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean-bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penchev, Gaël Liu, Francesco Visin, Kathleen Kenealy, Lucas Beyer, Xiaohai Zhai, Anton Tsitsulin , et al. (191 additional authors not shown)

Abstract: We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision understanding abilities, a wider coverage of languages and longer context - at least 128K tokens. We also change the architecture of the model to reduce the KV-cache memory that tends to explode with long context. This is achie… ▽ More We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision understanding abilities, a wider coverage of languages and longer context - at least 128K tokens. We also change the architecture of the model to reduce the KV-cache memory that tends to explode with long context. This is achieved by increasing the ratio of local to global attention layers, and keeping the span on local attention short. The Gemma 3 models are trained with distillation and achieve superior performance to Gemma 2 for both pre-trained and instruction finetuned versions. In particular, our novel post-training recipe significantly improves the math, chat, instruction-following and multilingual abilities, making Gemma3-4B-IT competitive with Gemma2-27B-IT and Gemma3-27B-IT comparable to Gemini-1.5-Pro across benchmarks. We release all our models to the community. △ Less

Submitted 25 March, 2025; originally announced March 2025.

Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through Intersection

Authors: Bo Leng, Ran Yu, Wei Han, Lu Xiong, Zhuoren Li, Hailong Huang

Abstract: Applying reinforcement learning to autonomous driving has garnered widespread attention. However, classical reinforcement learning methods optimize policies by maximizing expected rewards but lack sufficient safety considerations, often putting agents in hazardous situations. This paper proposes a risk-aware reinforcement learning approach for autonomous driving to improve the safety performance w… ▽ More Applying reinforcement learning to autonomous driving has garnered widespread attention. However, classical reinforcement learning methods optimize policies by maximizing expected rewards but lack sufficient safety considerations, often putting agents in hazardous situations. This paper proposes a risk-aware reinforcement learning approach for autonomous driving to improve the safety performance when crossing the intersection. Safe critics are constructed to evaluate driving risk and work in conjunction with the reward critic to update the actor. Based on this, a Lagrangian relaxation method and cyclic gradient iteration are combined to project actions into a feasible safe region. Furthermore, a Multi-hop and Multi-layer perception (MLP) mixed Attention Mechanism (MMAM) is incorporated into the actor-critic network, enabling the policy to adapt to dynamic traffic and overcome permutation sensitivity challenges. This allows the policy to focus more effectively on surrounding potential risks while enhancing the identification of passing opportunities. Simulation tests are conducted on different tasks at unsignalized intersections. The results show that the proposed approach effectively reduces collision rates and improves crossing efficiency in comparison to baseline algorithms. Additionally, our ablation experiments demonstrate the benefits of incorporating risk-awareness and MMAM into RL. △ Less

Submitted 27 March, 2025; v1 submitted 25 March, 2025; originally announced March 2025.

Comments: 11 pages, 10 figures

Towards Transformer-Based Aligned Generation with Self-Coherence Guidance

Authors: Shulei Wang, Wang Lin, Hai Huang, Hanting Wang, Sihang Cai, WenKang Han, Tao Jin, Jingyuan Chen, Jiacheng Sun, Jieming Zhu, Zhou Zhao

Abstract: We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-concept attribute binding challenges. Previous U-Net-based methods primarily optimized the latent space, but their direct application to Tra… ▽ More We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-concept attribute binding challenges. Previous U-Net-based methods primarily optimized the latent space, but their direct application to Transformer-based architectures has shown limited effectiveness. Our method addresses these challenges by directly optimizing cross-attention maps during the generation process. Specifically, we introduce Self-Coherence Guidance, a method that dynamically refines attention maps using masks derived from previous denoising steps, ensuring precise alignment without additional training. To validate our approach, we constructed more challenging benchmarks for evaluating coarse-grained attribute binding, fine-grained attribute binding, and style binding. Experimental results demonstrate the superior performance of our method, significantly surpassing other state-of-the-art methods across all evaluated tasks. Our code is available at https://scg-diffusion.github.io/scg-diffusion. △ Less

Submitted 22 March, 2025; originally announced March 2025.

Comments: Accepted by CVPR 2025

Developing Critical Thinking in Second Language Learners: Exploring Generative AI like ChatGPT as a Tool for Argumentative Essay Writing

Authors: Simon Suh, Jihyuk Bang, Ji Woo Han

Abstract: This study employs the Paul-Elder Critical Thinking Model and Tan's argumentative writing framework to create a structured methodology. This methodology, ChatGPT Guideline for Critical Argumentative Writing (CGCAW) framework, integrates the models with ChatGPT's capabilities to guide L2 learners in utilizing ChatGPT to enhance their critical thinking skills. A quantitative experiment was conducted… ▽ More This study employs the Paul-Elder Critical Thinking Model and Tan's argumentative writing framework to create a structured methodology. This methodology, ChatGPT Guideline for Critical Argumentative Writing (CGCAW) framework, integrates the models with ChatGPT's capabilities to guide L2 learners in utilizing ChatGPT to enhance their critical thinking skills. A quantitative experiment was conducted with 10 participants from a state university, divided into experimental and control groups. The experimental group utilized the CGCAW framework, while the control group used ChatGPT without specific guidelines. Participants wrote an argumentative essay within a 40-minute timeframe, and essays were evaluated by three assessors: ChatGPT, Grammarly, and a course instructor. Results indicated that the experimental group showed improvements in clarity, logical coherence, and use of evidence, demonstrating ChatGPT's potential to enhance specific aspects of argumentative writing. However, the control group performed better in overall language mechanics and articulation of main arguments, indicating areas where the CGCAW framework could be further refined. This study highlights the need for further research to optimize the use of AI tools like ChatGPT in L2 learning environments to enhance critical thinking and writing skills. △ Less

Submitted 21 March, 2025; originally announced March 2025.

Comments: 12 pages, 3 figures. Uses Paul-Elder Critical Thinking Model and Tan's argumentative writing framework. Includes an experimental study with 10 participants

ACM Class: I.2.7; K.3.1

HAR-DoReMi: Optimizing Data Mixture for Self-Supervised Human Activity Recognition Across Heterogeneous IMU Datasets

Authors: Lulu Ban, Tao Zhu, Xiangqing Lu, Qi Qiu, Wenyong Han, Shuangjian Li, Liming Chen, Kevin I-Kai Wang, Mingxing Nie, Yaping Wan

Abstract: Cross-dataset Human Activity Recognition (HAR) suffers from limited model generalization, hindering its practical deployment. To address this critical challenge, inspired by the success of DoReMi in Large Language Models (LLMs), we introduce a data mixture optimization strategy for pre-training HAR models, aiming to improve the recognition performance across heterogeneous datasets. However, direct… ▽ More Cross-dataset Human Activity Recognition (HAR) suffers from limited model generalization, hindering its practical deployment. To address this critical challenge, inspired by the success of DoReMi in Large Language Models (LLMs), we introduce a data mixture optimization strategy for pre-training HAR models, aiming to improve the recognition performance across heterogeneous datasets. However, directly applying DoReMi to the HAR field encounters new challenges due to the continuous, multi-channel and intrinsic heterogeneous characteristics of IMU sensor data. To overcome these limitations, we propose a novel framework HAR-DoReMi, which introduces a masked reconstruction task based on Mean Squared Error (MSE) loss. By raplacing the discrete language sequence prediction task, which relies on the Negative Log-Likelihood (NLL) loss, in the original DoReMi framework, the proposed framework is inherently more appropriate for handling the continuous and multi-channel characteristics of IMU data. In addition, HAR-DoReMi integrates the Mahony fusion algorithm into the self-supervised HAR pre-training, aiming to mitigate the heterogeneity of varying sensor orientation. This is achieved by estimating the sensor orientation within each dataset and facilitating alignment with a unified coordinate system, thereby improving the cross-dataset generalization ability of the HAR model. Experimental evaluation on multiple cross-dataset HAR transfer tasks demonstrates that HAR-DoReMi improves the accuracy by an average of 6.51%, compared to the current state-of-the-art method with only approximately 30% to 50% of the data usage. These results confirm the effectiveness of HAR-DoReMi in improving the generalization and data efficiency of pre-training HAR models, underscoring its significant potential to facilitate the practical deployment of HAR technology. △ Less

Submitted 16 March, 2025; originally announced March 2025.

Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis

Authors: Chanyoung Kim, Dayun Ju, Jinyeong Kim, Woojung Han, Roberto Alcover-Couso, Seong Jae Hwang

Abstract: As recent text-conditioned diffusion models have enabled the generation of high-quality images, concerns over their potential misuse have also grown. This issue is critical in the medical domain, where text-conditioned generated medical images could enable insurance fraud or falsified records, highlighting the urgent need for reliable safeguards against unethical use. While watermarking techniques… ▽ More As recent text-conditioned diffusion models have enabled the generation of high-quality images, concerns over their potential misuse have also grown. This issue is critical in the medical domain, where text-conditioned generated medical images could enable insurance fraud or falsified records, highlighting the urgent need for reliable safeguards against unethical use. While watermarking techniques have emerged as a promising solution in general image domains, their direct application to medical imaging presents significant challenges. A key challenge is preserving fine-grained disease manifestations, as even minor distortions from a watermark may lead to clinical misinterpretation, which compromises diagnostic integrity. To overcome this gap, we present MedSign, a deep learning-based watermarking framework specifically designed for text-to-medical image synthesis, which preserves pathologically significant regions by adaptively adjusting watermark strength. Specifically, we generate a pathology localization map using cross-attention between medical text tokens and the diffusion denoising network, aggregating token-wise attention across layers, heads, and time steps. Leveraging this map, we optimize the LDM decoder to incorporate watermarking during image synthesis, ensuring cohesive integration while minimizing interference in diagnostically critical regions. Experimental results show that our MedSign preserves diagnostic integrity while ensuring watermark robustness, achieving state-of-the-art performance in image quality and detection accuracy on MIMIC-CXR and OIA-ODIR datasets. △ Less

Submitted 11 March, 2025; originally announced March 2025.

Vector Quantized Feature Fields for Fast 3D Semantic Lifting

Authors: George Tang, Aditya Agarwal, Weiqiao Han, Trevor Darrell, Yutong Bai

Abstract: We generalize lifting to semantic lifting by incorporating per-view masks that indicate relevant pixels for lifting tasks. These masks are determined by querying corresponding multiscale pixel-aligned feature maps, which are derived from scene representations such as distilled feature fields and feature point clouds. However, storing per-view feature maps rendered from distilled feature fields is… ▽ More We generalize lifting to semantic lifting by incorporating per-view masks that indicate relevant pixels for lifting tasks. These masks are determined by querying corresponding multiscale pixel-aligned feature maps, which are derived from scene representations such as distilled feature fields and feature point clouds. However, storing per-view feature maps rendered from distilled feature fields is impractical, and feature point clouds are expensive to store and query. To enable lightweight on-demand retrieval of pixel-aligned relevance masks, we introduce the Vector-Quantized Feature Field. We demonstrate the effectiveness of the Vector-Quantized Feature Field on complex indoor and outdoor scenes. Semantic lifting, when paired with a Vector-Quantized Feature Field, can unlock a myriad of applications in scene representation and embodied intelligence. Specifically, we showcase how our method enables text-driven localized scene editing and significantly improves the efficiency of embodied question answering. △ Less

Submitted 9 March, 2025; originally announced March 2025.