KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Paper • 2606.03458 • Published • 53 •
10
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎🔠
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
View all activity
Organizations
commented 3
papers 3 days ago
commented a
paper 4 days ago
commented a
paper 6 days ago
commented a
paper 11 days ago
commented a
paper 12 days ago
commented 2
papers 17 days ago
commented a
paper 18 days ago
commented a
paper 22 days ago
commented a
paper 24 days ago
commented 6
papers 25 days ago
Reliable Chain-of-Thought via Prefix Consistency
Paper • 2605.07654 • Published • 1 •
3
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
Paper • 2605.12460 • Published • 17 •
2
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
Paper • 2605.10977 • Published • 10 •
2
LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models
Paper • 2605.11011 • Published • 9 •
2
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
Paper • 2605.07579 • Published • 18 •
3
$δ$-mem: Efficient Online Memory for Large Language Models
Paper • 2605.12357 • Published • 125 •
5
[Support] Community Articles
🚀🔥 2
106
#5 opened about 2 years ago
by 
victor
commented a
paper 27 days ago