activity
20242026
most citedPaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review

2 citations · 2 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CL20262 cited

PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review

Songjun Tu, Yiwen Ma, Jiahao Lin +6

Large language models can generate fluent peer reviews, yet their assessments often lack sufficient critical rigor when substantive issues are subtle and distributed across a paper…

cs.MM2025

Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization

Songjun Tu, Qichao Zhang, Jingbo Sun +6

While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: p…

cs.CL2025

Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL

Songjun Tu, Jiahao Lin, Qichao Zhang +4

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce…

cs.CL2025

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

Songjun Tu, Jiahao Lin, Xiangyu Tian +8

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. Ho…

cs.LG2024

Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model

Songjun Tu, Jingbo Sun, Qichao Zhang +2

Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-tim…