1 citations · 1 across the 17 of their papers we have counts for
8 papers · 1 filter
ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training
Zhihao Zhang, Mingqi Wu, Qiaole Dong +15
Continual post-training of large multimodal models should add new capabilities while preserving those from pre-training, and the two goals pull in opposite directions. SFT gives ex…
Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection
Senjie Jin, Peixin Wang, Boyang Liu +8
While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether t…
Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision Support
Chen Zhan, Xihe Qiu, Xiaoyu Tan +8
Large language models perform well on static medical examinations, yet clinical diagnosis often requires iterative evidence gathering under uncertainty. Building on prior interacti…
ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
Wanghan Xu, Yuhao Zhou, Hengyuan Zhao +8
Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user criticism. This i…
When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation
Shuowei Li, Yuming Zhao, Parth Bhalerao +1
Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single prompt remains underexplored. We…
How Large Language Models Balance Internal Knowledge with User and Document Assertions
Shuowei Li, Haoxin Li, Wenda Chu +1
Large language models (LLMs) often need to balance their internal parametric knowledge with external information, such as user beliefs and content from retrieved documents, in real…
Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling
Kai Ye, Qingtao Pan, Shuo Li
Large language models (LLMs) need reliable test-time control of hallucinations. Existing conformal methods for LLMs typically provide only \emph{marginal} guarantees and rely on a…
ChartE: A Comprehensive Benchmark for End-to-End Chart Editing
Shuo Li, Jiajun Sun, Zhekai Wang +9
Charts are a fundamental visualization format for structured data analysis. Enabling end-to-end chart editing according to user intent is of great practical value, yet remains chal…