12 papers
ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning
Zhenrong Zhang, Fei Wu, Jun Du +2
The paper presents ReDiPPO, a PPO-based reinforcement learning framework that leverages reference answers to guide value estimation and reweights token-level advantages based on di…
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
Hanbo Cheng, Limin Lin, Ruo Zhang +2
Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing…
THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Qikai Chang, Zhenrong Zhang, Pengfei Hu +6
Large Language Models (LLMs) have made remarkable progress in mathematical reasoning, but still continue to struggle with high-precision tasks like numerical computation and formal…
Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning
Fei Wu, Zhenrong Zhang, Qikai Chang +3
Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained adva…
See then Tell: Enhancing Key Information Extraction with Vision Grounding
Shuhang Liu, Zhenrong Zhang, Pengfei Hu +5
In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) me…
Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration
Yicheng Pan, Zhenrong Zhang, Pengfei Hu +6
Recent advances in Multimodal Large Language Models (MLLMs) have achieved remarkable progress in general domains and demonstrated promise in multimodal mathematical reasoning. Howe…