Peizhen Li

Peizhen

·

https://lipzh5.github.io/

lipzh5

AI & ML interests

Reinforcement Learning; LLM Post-Training;Multimodal LLM; Embodied AI

Recent Activity

upvoted a paper 6 days ago

Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation

submitted a paper 6 days ago

Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation

authored a paper 7 days ago

REALM: A Coarse-to-Fine Generative Framework for Embodied Reactive Listening

View all activity

Organizations

upvoted a paper 6 days ago

Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation

Paper • 2609.34848 • Published 8 days ago • 6

upvoted 2 papers 7 days ago

RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training

Paper • 2608.18682 • Published Aug 19 • 5

REALM: A Coarse-to-Fine Generative Framework for Embodied Reactive Listening

Paper • 2609.33095 • Published 9 days ago • 21

upvoted a paper 8 days ago

PACE: Persona Adaptation through Conversational Elicitation in Human-Robot Interaction

Paper • 2607.15579 • Published Jul 21 • 1

upvoted a paper 29 days ago

X2C: A Dataset Featuring Nuanced Facial Expressions for Realistic Humanoid Imitation

Paper • 2505.11146 • Published May 16, 2025 • 1

upvoted a paper about 1 month ago

Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States

Paper • 2609.04196 • Published Sep 3 • 71

upvoted an article about 1 month ago

Article

VLANeXt: A Simple and Research-Oriented Codebase for Robotics Research

cavanloy

•

Aug 31

• 23