most citedThe Fact Selection Problem in LLM-Based Program Repair

4 citations · 4 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning

Haoxiang Sun, Lizhen Xu, Bing Zhao +5

Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). Howe…