khtsly

khtsly's activity

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

commented a paper 44 minutes ago

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

Paper • 2608.16072 • Published 1 day ago • 42 •

2

upvoted a paper about 1 hour ago

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

Paper • 2608.16072 • Published 1 day ago • 42

upvoted a paper about 3 hours ago

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

Paper • 2608.14783 • Published 5 days ago • 15

commented a paper about 3 hours ago

Dion3: Full-Stack Orthogonal Updates

Paper • 2608.11612 • Published 7 days ago • 6 •

3

upvoted a paper about 3 hours ago

Dion3: Full-Stack Orthogonal Updates

Paper • 2608.11612 • Published 7 days ago • 6

updated a dataset about 14 hours ago

khtsly/cache_stage2

Updated about 14 hours ago • 518

published a dataset about 14 hours ago

khtsly/cache_stage2

Updated about 14 hours ago • 518

updated a model 1 day ago

khtsly/luau-coder-1.0-preview-tokenizer

Updated 1 day ago

published a model 1 day ago

khtsly/luau-coder-1.0-preview-tokenizer

Updated 1 day ago

upvoted a paper 3 days ago

Maglev: Sliding Recurrent Memory

Paper • 2608.02870 • Published 14 days ago • 14

commented a paper 3 days ago

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

Paper • 2608.12149 • Published 7 days ago • 30 •

4

upvoted a paper 3 days ago

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

Paper • 2608.12149 • Published 7 days ago • 30

upvoted 2 papers 7 days ago

Motif 3: Technical Report

Paper • 2608.09119 • Published 9 days ago • 43

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

Paper • 2608.09819 • Published 9 days ago • 334

upvoted a paper 8 days ago

Skaling: Chinchilla's Exponents Meet Kaplan's Coupling

Paper • 2608.07222 • Published 12 days ago • 9

updated 2 datasets 9 days ago

khtsly/luau-repo-docs-text

Viewer • Updated 9 days ago • 1.83k • 73 • 1

khtsly/luau-stack-hq

Viewer • Updated 9 days ago • 12.2k • 88 • 2

upvoted a paper 12 days ago

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

Paper • 2607.24027 • Published 23 days ago • 37

New activity in AxiomicLabs/GPT-X2.5-135M 13 days ago

dataset quality

2

#5 opened 13 days ago by

khtsly

upvoted a paper 14 days ago

DAPD: Dual-Anchored Policy Distillation

Paper • 2608.01735 • Published 16 days ago • 149