Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning
Yongxin Wang, Zhicheng Yang, Meng Cao +5
Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stal…
cs.LG2026
Training and Benchmarking Code Generation for Physics-Inspired Animations
Yanan Wang, Renxi Wang, Yongxin Wang +5
Large language models (LLMs) have been widely studied in areas such as mathematical reasoning, complex coding, and scientific problem solving. However, their ability to generate ex…