drexelliu

yl926

6 2

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 12 hours ago

Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs

liked a model 4 days ago

tinyopsec/Jeesup-svd-safety-l3_swift_remove40_swapgapiter_evfront_b010-GGUF

upvoted a paper 6 days ago

Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning

View all activity

Organizations

None yet

upvoted a paper about 12 hours ago

Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs

Paper • 2609.33477 • Published about 1 month ago • 9

upvoted a paper 6 days ago

Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning

Paper • 2609.38658 • Published 29 days ago • 14

upvoted 2 papers 6 months ago

Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression

Paper • 2604.01609 • Published Apr 2 • 15

When AI Navigates the Fog of War

Paper • 2603.16642 • Published Mar 17 • 32

upvoted an article 7 months ago

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

+7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 195

upvoted a paper 9 months ago

KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs

Paper • 2602.05929 • Published Feb 5 • 2