MMODELYST
People/Junfeng Fang
PPL

Junfeng Fang

Papers (4)
Learning to Act under Noise: Enhancing Agent Robustness via Noisy EnvironmentsUniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMsRubric-based On-policy DistillationOn the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR