What Does Privileged Information Add to On-Policy Self-Distillation?
Paper • 2609.20612 • Published • 29
Adam Lee
Abecid
AI & ML interests
3D, Gaussian Splatting, Diffusion
Recent Activity
upvoted a paper about 2 hours ago
What Does Privileged Information Add to On-Policy Self-Distillation? upvoted a paper 5 days ago
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation upvoted a paper 5 days ago
Discovery Foundation Models: Toward Open-Ended Discovery IntelligenceOrganizations
upvoted a paper about 2 hours ago
upvoted 2
papers 5 days ago
upvoted a paper 8 days ago
upvoted a paper 10 days ago
upvoted 2
papers 11 days ago
upvoted 3
papers 12 days ago
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 • 53
MaxKernel: Agentic Kernel Generation for TPUs
Paper • 2609.04523 • Published • 18
upvoted 3
papers 15 days ago
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
Paper • 2609.04196 • Published • 69
Principia: Relational Physics Tests for Video Models
Paper • 2609.04200 • Published • 16
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Paper • 2608.31100 • Published • 40
upvoted an article 15 days ago
Article
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
- +1
iamleonie, burtenshaw, sergiopaniego
• • 126 upvoted a paper 16 days ago
upvoted an article 16 days ago
Article
Training a coding model to paint watercolours with TRL and OpenEnv
sergiopaniego
• • 70 upvoted 2
papers 17 days ago
upvoted 2
papers 18 days ago