ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Paper • 2607.13124 • Published • 11
YuhaoChen
veoxl
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation upvoted a paper 7 months ago
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length upvoted a paper over 2 years ago
ShortGPT: Layers in Large Language Models are More Redundant Than You
ExpectOrganizations
None yet