Data-Free On-Policy Distillation: How Far Can We Go Without External Data?
Paper • 2609.14193 • Published • 11
Tianyue Wang
Physicsmile
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
Data-Free On-Policy Distillation: How Far Can We Go Without External Data? liked a dataset about 1 month ago
Physicsmile/WISER upvoted a paper 2 months ago
Continual Learning in TransitionOrganizations
None yet
upvoted a paper 2 days ago
liked a
dataset about 1 month ago
upvoted a paper 2 months ago
updated 3
datasets 3 months ago
published 3
datasets 3 months ago
published a
dataset 5 months ago
upvoted a paper 5 months ago
updated a
dataset 5 months ago
published a
dataset 5 months ago
updated a
model 5 months ago
published a
model 5 months ago
published a
dataset 6 months ago
upvoted 4
papers 6 months ago
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
Paper • 2604.12627 • Published • 68
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models
Paper • 2604.04780 • Published • 9
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Paper • 2604.02288 • Published • 32
PLUME: Latent Reasoning Based Universal Multimodal Embedding
Paper • 2604.02073 • Published • 11