26 citations · 89 across the 49 of their papers we have counts for
14 papers · 1 filter
Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards
Shangyu Xing, Siyuan Wang, Chenyuan Yang +2
Reinforcement Learning with Verifiable Rewards (RLVR), particularly with algorithms like Group Relative Policy Optimization (GRPO), has proven highly effective in enhancing the rea…
HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games
Jingcong Liang, Shijun Wan, Xuehai Wu +5
Large Reasoning Models (LRMs) have demonstrated impressive performance on complex tasks, including logical puzzle games that require deriving solutions satisfying all constraints.…
Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
Zejun Li, Yingxiu Zhao, Jiwen Zhang +6
Current visual reasoning methods mainly focus on exploring specific reasoning modes. Although improvements can be achieved in particular domains, they struggle to develop general r…
Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
Huihan Li, You Chen, Siyuan Wang +4
Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about the extent to which their success relies on memo…
Simple o3: Towards Interleaved Vision-Language Reasoning
Ye Wang, Qianglong Chen, Zejun Li +4
Multimodal Large Language Models (MLLMs) have shown impressive performance on vision-language tasks, but their long Chain-of-Thought (CoT) capabilities in multimodal scenarios rema…
MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models
Dianyi Wang, Siyuan Wang, Zejun Li +6
Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across multi-modal tasks by scaling model size and training data. However, these dense LVLMs incur sig…
Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments
Zheng Jia, Shengbin Yue, Wei Chen +5
The gap between static benchmarks and the dynamic nature of real-world legal practice poses a key barrier to advancing legal intelligence. To this end, we introduce J1-ENVS, the fi…
Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
Dianyi Wang, Wei Song, Yikun Wang +4
Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process…
AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs
Xuanwen Ding, Chengjun Pan, Zejun Li +3
Evaluating multimodal large language models (MLLMs) is increasingly expensive, as the growing size and cross-modality complexity of benchmarks demand significant scoring efforts. T…
Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models
Jingcong Liang, Siyuan Wang, Miren Tian +3
Mixture-of-Experts (MoE) enables efficient scaling of large language models (LLMs) with sparsely activated experts during inference. To effectively deploy large MoE models on memor…
OViP: Online Vision-Language Preference Learning for VLM Hallucination
Shujun Liu, Siyuan Wang, Zejun Li +3
Large vision-language models (LVLMs) remain vulnerable to hallucination, often generating content misaligned with visual inputs. Although recent training-based approaches aim to mi…
How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation
Zhuohang Long, Siyuan Wang, Shujun Liu +3
Jailbreak attacks, where harmful prompts bypass generative models' built-in safety, raise serious concerns about model vulnerability. While many defense methods have been proposed,…
Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction
Shengbin Yue, Ting Huang, Zheng Jia +5
Large Language Models (LLMs) have significantly advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios. This paper i…
Stepwise Informativeness Search for Efficient and Effective LLM Reasoning
Siyuan Wang, Enda Zhao, Zhongyu Wei +1
Advances in Large Language Models (LLMs) have significantly improved multi-step reasoning through generating free-text rationales. However, recent studies show that LLMs tend to lo…