khtsly

khtsly's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 8 hours ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published 5 days ago • 57

upvoted 3 papers about 14 hours ago

Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction

Paper • 2609.13285 • Published 8 days ago • 58

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published 2 days ago • 369

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 2 days ago • 263

upvoted a paper 1 day ago

Language Self-Play For Data-Free Training

Paper • 2509.07414 • Published Sep 9, 2025 • 32

upvoted 2 papers 2 days ago

HyQuant: Hybrid-Precision Quantization for LLM Attention

Paper • 2608.27875 • Published 19 days ago • 31

Solar Open 2 Technical Report

Paper • 2607.20062 • Published Jul 24 • 6

upvoted a paper 3 days ago

Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention

Paper • 2606.26560 • Published Jun 25 • 3

upvoted a paper 7 days ago

Kalman Delta Networks: Uncertainty-aware Associative Memory

Paper • 2609.07816 • Published 9 days ago • 29

upvoted 2 papers 8 days ago

Enoki: Efficient Multi-Level Hallucination Detection

Paper • 2609.00581 • Published 15 days ago • 28

Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

Paper • 2609.02998 • Published 14 days ago • 20

upvoted 4 papers 9 days ago

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Paper • 2609.05295 • Published 12 days ago • 16

Group Adaptive Clipping Policy Optimization

Paper • 2609.00444 • Published 16 days ago • 10

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published 13 days ago • 17

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

Paper • 2609.05275 • Published 12 days ago • 23

upvoted a paper 10 days ago

MDN: Parallelizing Stepwise Momentum for Delta Linear Attention

Paper • 2605.05838 • Published May 7 • 6

upvoted 4 papers 12 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 13 days ago • 184

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

Paper • 2609.04098 • Published 13 days ago • 83

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 13 days ago • 97

Post-Training Language Models for Gold-Medal Performance in Coding Competitions

Paper • 2609.02849 • Published 14 days ago • 12