Recovering Reliable Supervision via Critique-Guided On-Policy Distillation
Paper • 2610.20572 • Published • 80
Karan Verma
Karanvermasuw
·
AI & ML interests
Interested in machine learning, NLP and open source AI.
Recent Activity
upvoted a paper 2 days ago
Recovering Reliable Supervision via Critique-Guided On-Policy Distillation liked a model 15 days ago
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 liked a model 15 days ago
Edge0/Audio8-ASR-InfiniteOrganizations
None yet
upvoted a paper 2 days ago