13 papers
Beyond the Mean: Multi-Moment Policy Optimization for LLM Reasoning
Yijun Zhang, Yule Xie, Jiaxin Ding +4
Reinforcement learning has become a central paradigm for improving the reasoning capabilities of large language models. Existing methods generally aim to reduce the failure probabi…
DAVET: Denoising-Aware Visual Evidence Trajectory Allocation for Diffusion Vision-Language Models
Yongkang Zhou, Xiang Xia, Cheng Yan +2
Diffusion vision-language models (dVLMs) iteratively denoise masked responses while conditioning each denoising step on visual evidence, making visual conditioning a substantial re…
UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention
Cheng Yan, Guangyang Ye, Wuyang Zhang +5
While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can also exacerbate overthinking and…
Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents
Yijun Zhang, Fan Xu, Jiaxin Ding +6
Reinforcement learning has become a promising paradigm for improving large language model (LLM) agents on long-horizon search tasks, where the agent must make a sequence of interme…
Multimodal Representation Alignment for Cross-modal Information Retrieval
Fan Xu, Luis A. Leiva
Different machine learning models can represent the same underlying concept in different ways. This variability is particularly valuable for in-the-wild multimodal retrieval, where…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +306
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…