5 papers
LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling
Zecheng Tang, Baibei Ji, Quantong Qiu +4
Reward model (RM) plays a pivotal role in aligning large language model (LLM) with human preferences. As real-world applications increasingly involve long history trajectories, e.g…
SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning
Yuyang Ding, Xinyu Shi, Juntao Li +3
Process reward models (PRMs) offer fine-grained, step-level evaluations that facilitate deeper reasoning processes in large language models (LLMs), proving effective in complex tas…
Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding
Wanfu Wang, Qipeng Huang, Guangquan Xue +2
Vision Language Models (VLMs) have recently achieved significant progress in bridging visual perception and linguistic reasoning. Recently, OpenAI o3 model introduced a zoom-in sea…
Unlocking Recursive Thinking of LLMs: Alignment via Refinement
Haoke Zhang, Xiaobo Liang, Cunxiang Wang +2
The OpenAI o1-series models have demonstrated that leveraging long-form Chain of Thought (CoT) can substantially enhance performance. However, the recursive thinking capabilities o…
Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch
Yuyang Ding, Xinyu Shi, Xiaobo Liang +4
Improving the mathematical reasoning capabilities of Large Language Models (LLMs) is critical for advancing artificial intelligence. However, access to extensive, diverse, and high…