ReFreeKV: Towards Threshold-Free KV Cache Compression
Paper • 2502.16886 • Published • 47
🔄 In a Training Loop
Urro
urroxyz
·
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
upvoted a paper 2 days ago
ReFreeKV: Towards Threshold-Free KV Cache Compression updated a collection 2 days ago
WTF GENIUS PAPERSOrganizations
upvoted 7
papers 2 days ago
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Paper • 2606.31315 • Published • 71
Multi-Block Diffusion Language Models
Paper • 2606.29215 • Published • 30
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Paper • 2606.32032 • Published • 21
AsyncOPD: How Stale Can On-Policy Distillation Be?
Paper • 2606.24143 • Published • 29
MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
Paper • 2606.30406 • Published • 11
DOPD: Dual On-policy Distillation
Paper • 2606.30626 • Published • 91
upvoted 3
papers 3 days ago
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
Paper • 2606.18394 • Published • 35
Information-Aware KV Cache Compression for Long Reasoning
Paper • 2606.26875 • Published • 11
Simplified Sparse Attention via Gist Tokens
Paper • 2604.20920 • Published • 5
upvoted 2
papers 5 days ago
upvoted a paper 6 days ago
upvoted a changelog 7 days ago
Hugging Face Changelog
Share your feedback with us
• 104
upvoted 3
papers 7 days ago
CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
Paper • 2502.21074 • Published • 5
Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining
Paper • 2606.16246 • Published • 4
Tapered Language Models
Paper • 2606.23670 • Published • 9
upvoted 2
papers 11 days ago
upvoted a paper 12 days ago