Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Paper • 2605.16928 • Published • 94
Weizhong Huang
huangwz
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 months ago
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models upvoted a paper 4 months ago
MOVA: Towards Scalable and Synchronized Video-Audio GenerationOrganizations
upvoted a paper 25 days ago
upvoted a paper 3 months ago
upvoted a paper 4 months ago
upvoted an article over 1 year ago
Article
KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 347