2 papers
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…
cs.LG2024
SVM: Soft-margin SVMs with -norm Hinge Loss
Haoxiang Sun
Support Vector Machines (SVMs) based on hinge loss have been extensively discussed and applied to various binary classification tasks. These SVMs achieve a balance between margin m…