MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper
•
2601.07832
•
Published
•
46
Martin
progmars
AI & ML interests
None yet
Recent Activity
liked
a model
about 14 hours ago
nvidia/canary-1b-v2
new activity
2 days ago
progmars/ltx-2-19b-dev-fp8_e5m2:Do you have the distilled version?
updated
a model
2 days ago
progmars/ltx-2-19b-dev-fp8_e5m2
Organizations
None yet
upvoted
a
paper
5 days ago
upvoted
an
article
about 2 months ago
Article
Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers
•
343