8 papers
ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
Jingpei Wu, Xiao Han, Weixiang Shen +3
Visual question answering increasingly requires multi-step reasoning. Recent post-training with reinforcement learning under verifiable rewards (RLVR) and Group Relative Policy Opt…
DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
Jiazhen Pan, Weixiang Shen, Jun Li +7
Medical diagnosis is not a single prediction from a fully specified vignette. It is a sequential workup: clinicians decide what evidence to obtain, revise a differential diagnosis,…
RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
Chengzhi Shen, Weixiang Shen, Tobias Susetzky +7
Intensive care units (ICU) generate long, dense and evolving streams of clinical information, where physicians must repeatedly reassess patient states under time pressure, undersco…
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Yifan Zhang, Liang Hu, Haofeng Sun +12
Despite recent progress in multimodal agentic systems, existing approaches often treat image manipulation and web search as disjoint capabilities, rely heavily on costly reinforcem…
Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization
Junjie Lu, Yuliang Liu, Chaofeng Qu +4
Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular,…
What Do Latent Action Models Actually Learn?
Chuheng Zhang, Tim Pearce, Pushi Zhang +5
Latent action models (LAMs) aim to learn action-relevant changes from unlabeled videos by compressing changes between frames as latents. However, differences between video frames c…
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Yuliang Liu, Junjie Lu, Zhaoling Chen +10
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefin…
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Zhiyuan Hu, Yuliang Liu, Jinman Zhao +8
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts t…