RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning
Paper
•
2409.14674
•
Published
•
44
•
6
Dai
Yinpei
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
9 days ago
Autoregressive Adversarial Post-Training for Real-Time Interactive Video
Generation
published
a model
about 1 month ago
Yinpei/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Organizations
Yinpei's activity
commented
2
papers
9 months ago