khtsly

khtsly's activity

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

upvoted a paper about 8 hours ago

Full-bandwidth transformer

Paper • 2608.08888 • Published 12 days ago • 22

upvoted 3 papers 1 day ago

AVA-Encoder: Towards Agent-Native Video Representation Learning

Paper • 2608.12313 • Published 9 days ago • 40

ASI-Bench: At the Dawn of Artificial Superintelligence

Paper • 2608.17271 • Published 3 days ago • 55

RLP: Reinforcement as a Pretraining Objective

Paper • 2510.01265 • Published Sep 26, 2025 • 47

upvoted 3 papers 2 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 4 days ago • 145

MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling

Paper • 2608.14783 • Published 7 days ago • 19

Dion3: Full-Stack Orthogonal Updates

Paper • 2608.11612 • Published 9 days ago • 7

upvoted 2 papers 5 days ago

Maglev: Sliding Recurrent Memory

Paper • 2608.02870 • Published 16 days ago • 14

Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

Paper • 2608.12149 • Published 9 days ago • 30

upvoted 2 papers 9 days ago

Motif 3: Technical Report

Paper • 2608.09119 • Published 11 days ago • 46

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published 11 days ago • 336

upvoted a paper 11 days ago

Skaling: Chinchilla's Exponents Meet Kaplan's Coupling

Paper • 2608.07222 • Published 14 days ago • 9

upvoted a paper 14 days ago

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

Paper • 2607.24027 • Published 25 days ago • 37

upvoted a paper 16 days ago

DAPD: Dual-Anchored Policy Distillation

Paper • 2608.01735 • Published 18 days ago • 149

upvoted a paper 20 days ago

Multi-Head Attention Residuals

Paper • 2607.27230 • Published 30 days ago • 11

upvoted a paper 24 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 25 days ago • 497

upvoted 4 papers about 1 month ago

Understanding Reasoning from Pretraining to Post-Training

Paper • 2607.16097 • Published Jul 17 • 29

xHC: Expanded Hyper-Connections

Paper • 2607.14530 • Published Jul 16 • 56

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 193

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Paper • 2607.05147 • Published Jul 6 • 45