khtsly

khtsly's activity

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

upvoted a paper about 3 hours ago

Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation in Transformers

Paper • 2608.15062 • Published 2 days ago • 3

upvoted a paper 1 day ago

On-Policy Self-Distillation in Diffusion Models

Paper • 2608.24646 • Published 2 days ago • 53

upvoted an article 1 day ago

view article

Article

Granite 4.1 LLMs: How They’re Built

• 

ibm-granite

•

Apr 29

• 91

upvoted 2 papers 2 days ago

Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning

Paper • 2608.13914 • Published 13 days ago • 3

Prime Agent: A Self-Improving RLM Harness

Paper • 2608.23552 • Published 3 days ago • 40

upvoted a paper 3 days ago

Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts

Paper • 2608.20061 • Published 7 days ago • 43

upvoted a paper 6 days ago

FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving

Paper • 2608.19758 • Published 7 days ago • 18

upvoted a paper 7 days ago

Full-bandwidth transformer

Paper • 2608.08888 • Published 18 days ago • 22

upvoted 3 papers 8 days ago

AVA-Encoder: Towards Agent-Native Video Representation Learning

Paper • 2608.12313 • Published 15 days ago • 42

ASI-Bench: At the Dawn of Artificial Superintelligence

Paper • 2608.17271 • Published 9 days ago • 62

RLP: Reinforcement as a Pretraining Objective

Paper • 2510.01265 • Published Sep 26, 2025 • 47

upvoted 3 papers 9 days ago

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

Paper • 2608.16072 • Published 10 days ago • 149

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

Paper • 2608.14783 • Published 13 days ago • 19

Dion3: Full-Stack Orthogonal Updates

Paper • 2608.11612 • Published 15 days ago • 9

upvoted 2 papers 12 days ago

Maglev: Sliding Recurrent Memory

Paper • 2608.02870 • Published 22 days ago • 14

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

Paper • 2608.12149 • Published 15 days ago • 30

upvoted 2 papers 16 days ago

Motif 3: Technical Report

Paper • 2608.09119 • Published 17 days ago • 46

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

Paper • 2608.09819 • Published 17 days ago • 342

upvoted a paper 17 days ago

Skaling: Chinchilla's Exponents Meet Kaplan's Coupling

Paper • 2608.07222 • Published 20 days ago • 10

upvoted a paper 21 days ago

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

Paper • 2607.24027 • Published Jul 27 • 37