The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 271
Adam Lee
Abecid
AI & ML interests
3D, Gaussian Splatting, Diffusion
Recent Activity
View all activity
Organizations
upvoted a paper about 12 hours ago
upvoted a paper 3 days ago
upvoted 2
papers 12 days ago
upvoted a paper 16 days ago
upvoted a paper 17 days ago
upvoted a paper 20 days ago
upvoted a paper 21 days ago
upvoted 4
papers 23 days ago
The Attention Triangle in Audio-Video Models
Paper • 2609.03586 • Published • 44
EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents
Paper • 2609.01281 • Published • 15
To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation
Paper • 2608.05879 • Published • 9
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
Paper • 2609.03241 • Published • 54
upvoted a paper 24 days ago
upvoted 3
papers 27 days ago
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
Paper • 2609.04196 • Published • 71
Principia: Relational Physics Tests for Video Models
Paper • 2609.04200 • Published • 18
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Paper • 2608.31100 • Published • 42
upvoted an article 27 days ago
Article
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
- +1
iamleonie, burtenshaw, sergiopaniego
• • 143 upvoted a paper 28 days ago
upvoted an article 28 days ago
Article
Training a coding model to paint watercolours with TRL and OpenEnv
sergiopaniego
• • 76 upvoted a paper 29 days ago