7 papers
Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation
Tianyi Xiong, Zhengyuan Yang, Xiaofei Wang +10
Large vision-language models have shown strong progress in UI-to-code generation, yet their test-time self-evolution remains unstable. We first identify a fundamental obstacle, ter…
PhyCritic: Multimodal Critic Models for Physical AI
Tianyi Xiong, Shihao Wang, Guilin Liu +5
With the rapid development of large multimodal models, reliable judge and critic models have become essential for open-ended evaluation and preference alignment, providing pairwise…
R2-Router: A New Paradigm for LLM Routing with Reasoning
Jiaqi Xue, Qian Lou, Jiarong Xing +1
As LLMs proliferate with diverse capabilities and costs, LLM routing has emerged by learning to predict each LLM's quality and cost for a given query, then selecting the one with h…
Are We Evaluating the Edit Locality of LLM Model Editing Properly?
Wei Liu, Haomei Xu, Hongkai Liu +5
Model editing has recently emerged as a popular paradigm for efficiently updating knowledge in LLMs. A central desideratum of updating knowledge is to balance editing efficacy, i.e…
Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate
Chenxi Liu, Yanshuo Chen, Ruibo Chen +3
The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reaso…
Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models
Chenxi Liu, Junjie Liang, Yuqi Jia +4
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative…
GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning
Kelin Yu, Sheng Zhang, Harshit Soora +4
Recent advances have shown that video generation models can enhance robot learning by deriving effective robot actions through inverse dynamics. However, these methods heavily depe…