Yunfei Xie PRO

yunfeixie's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 10 days ago

yunfeixie/GPT-GEAR-RoboCasa-GR1-trial

Updated 10 days ago • 200

published a dataset 11 days ago

yunfeixie/GPT-GEAR-RoboCasa-GR1-trial

Updated 10 days ago • 200

authored 5 papers 14 days ago

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Paper • 2610.31670 • Published 21 days ago • 8

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published Sep 25 • 47

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

Paper • 2609.03199 • Published Sep 2 • 12

How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning

Paper • 2605.17570 • Published May 17

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

Paper • 2603.09022 • Published Mar 9 • 25

upvoted a paper 15 days ago

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Paper • 2610.31670 • Published 21 days ago • 8

submitted a paper to Daily Papers 15 days ago

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Paper • 2610.31670 • Published 21 days ago • 8

upvoted a paper about 2 months ago

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

Paper • 2609.22086 • Published Sep 18 • 30

commented a paper 2 months ago

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

Paper • 2609.03199 • Published Sep 2 • 12 •

4

liked a model 2 months ago

Rice-RobotPI-Lab/robotok-public

Robotics • Updated Sep 25 • 7

submitted a paper to Daily Papers 2 months ago

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

Paper • 2609.03199 • Published Sep 2 • 12

upvoted a paper 2 months ago

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

Paper • 2609.03199 • Published Sep 2 • 12

updated a model 7 months ago

yunfeixie/run_b_best

Updated Apr 22

published a model 7 months ago

yunfeixie/run_b_best

Updated Apr 22

updated a model 7 months ago

yunfeixie/vlm4vla-qwen25vl3b-bridge-step10k

Robotics • Updated Apr 22

published a model 7 months ago

yunfeixie/vlm4vla-qwen25vl3b-bridge-step10k

Robotics • Updated Apr 22

upvoted 2 papers 8 months ago

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published Mar 17 • 138

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

Paper • 2603.09022 • Published Mar 9 • 25