arxiv:2609.33095
Peizhen Li
Peizhen
·
AI & ML interests
Reinforcement Learning; LLM Post-Training;Multimodal LLM; Embodied AI
Recent Activity
submitted a paper 8 days ago
Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation authored a paper 9 days ago
REALM: A Coarse-to-Fine Generative Framework for Embodied Reactive ListeningOrganizations
