khtsly

khtsly's activity

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

upvoted 2 papers 3 days ago

Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute Width

Paper • 2610.41711 • Published 13 days ago • 9

P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors

Paper • 2611.03953 • Published 10 days ago • 67

upvoted a paper 4 days ago

Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout

Paper • 2611.08376 • Published 7 days ago • 14

upvoted a collection 5 days ago

Luau Coder 2.5

Collection

1 item • Updated 5 days ago • 1

upvoted a collection 6 days ago

Luau Coder 2.0

Collection

3 items • Updated 5 days ago • 1

upvoted 2 papers 12 days ago

Delta Attention Residuals

Paper • 2605.18855 • Published May 13 • 9

Recursive Language Models

Paper • 2512.24601 • Published Dec 31, 2025 • 102

upvoted a paper 13 days ago

Multi-Token Prediction Done Right

Paper • 2610.38331 • Published 15 days ago • 23

upvoted a paper 15 days ago

RSI Arena: Towards Recursive Self-Improvement with Human Feedback

Paper • 2610.33624 • Published 19 days ago • 27

upvoted a paper 18 days ago

A Fix for Softmax and Cross-Entropy

Paper • 2610.31642 • Published 21 days ago • 5

upvoted a paper 21 days ago

Cache Engineering for Agents

Paper • 2610.28577 • Published 23 days ago • 105

upvoted a paper 22 days ago

Breaking Diffusion: Parallel Reasoning with Draft Refinement

Paper • 2610.26542 • Published 24 days ago • 24

upvoted a paper 23 days ago

Kronecker Delta Rule for Long Context Linear Attention

Paper • 2610.26834 • Published 24 days ago • 32

upvoted a paper 24 days ago

Virtual Head Attention

Paper • 2610.17959 • Published about 1 month ago • 18

upvoted a paper 25 days ago

Native Hybrid Attention for Efficient Sequence Modeling

Paper • 2510.07019 • Published Oct 8, 2025 • 18

upvoted 4 papers 28 days ago

Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space

Paper • 2510.04476 • Published Oct 6, 2025 • 17

Continuum Attention

Paper • 2610.20586 • Published 29 days ago • 8

Long-Horizon RL Needs Muon

Paper • 2610.20256 • Published 29 days ago • 11

LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation

Paper • 2610.19975 • Published 29 days ago • 43

upvoted a paper 29 days ago

UltraBERT: Beyond the Limit of BERT Pre-Training

Paper • 2610.15028 • Published Oct 10 • 62