2 papers
cs.CL2026
RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
Yukun Chen, Jiaming Li, Longze Chen +10
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a prevailing paradigm for enhancing reasoning in Multimodal Large Language Models (MLLMs). However, relying sol…
cs.CL2026
Learning Ordinal Probabilistic Reward from Preferences
Longze Chen, Lu Wang, Renke Shan +6
Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) p…