khtsly

khtsly's activity

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

updated a model about 9 hours ago

khtsly/luau-coder-1.0-preview-small

Text Generation • 0.9B • Updated 18 minutes ago

published a model about 9 hours ago

khtsly/luau-coder-1.0-preview-small

Text Generation • 0.9B • Updated 18 minutes ago

upvoted a paper about 10 hours ago

MDN: Parallelizing Stepwise Momentum for Delta Linear Attention

Paper • 2605.05838 • Published May 7 • 6

updated a dataset about 15 hours ago

khtsly/cache_stage1

Updated about 15 hours ago • 19

published a dataset 1 day ago

khtsly/cache_stage1

Updated about 15 hours ago • 19

updated 2 datasets 1 day ago

khtsly/luau-repo-docs-text

Viewer • Updated 1 day ago • 1.85k • 93 • 1

khtsly/luau-stack-hq

Viewer • Updated 1 day ago • 17.9k • 166 • 2

upvoted a paper 2 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 4 days ago • 162

upvoted 3 papers 3 days ago

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

Paper • 2609.04098 • Published 4 days ago • 73

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

Paper • 2609.04172 • Published 4 days ago • 77

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

Paper • 2609.02849 • Published 5 days ago • 9

upvoted 3 papers 4 days ago

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published 5 days ago • 62

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model

Paper • 2607.22083 • Published Jul 27 • 10

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 6 days ago • 482

upvoted 3 papers 5 days ago

On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

Paper • 2608.30320 • Published 7 days ago • 53

Normalized Low-Rank Adaptation

Paper • 2608.31036 • Published 7 days ago • 50

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 7 days ago • 142

upvoted 2 papers 7 days ago

Self-Improving Pretraining: using post-trained models to pretrain better models

Paper • 2601.21343 • Published Jan 29 • 21

A Programming Paradigm for Spatiotemporal Composability

Paper • 2608.25512 • Published 12 days ago • 16

upvoted a paper 9 days ago

D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation

Paper • 2608.24987 • Published 13 days ago • 26