khtsly

khtsly's activity

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

liked a model about 10 hours ago

khtsly/luau-coder-1.0-preview-tokenizer

Updated Aug 17 • 1

liked a dataset about 10 hours ago

khtsly/roblox-luau-corpus

Viewer • Updated about 10 hours ago • 189k • 1

published a dataset about 10 hours ago

khtsly/roblox-luau-corpus

Viewer • Updated about 10 hours ago • 189k • 1

updated a dataset about 10 hours ago

khtsly/roblox-luau-corpus

Viewer • Updated about 10 hours ago • 189k • 1

liked a model 1 day ago

khtsly/Qwen3.8-Next-26B-A5.5B-N8B

37B • Updated 1 day ago • 25 • 1

updated a model 1 day ago

khtsly/Qwen3.8-Next-26B-A5.5B-N8B

37B • Updated 1 day ago • 25 • 1

published a model 1 day ago

khtsly/Qwen3.8-Next-26B-A5.5B-N8B

37B • Updated 1 day ago • 25 • 1

upvoted 2 papers 2 days ago

Bellman Policy Optimization

Paper • 2609.15987 • Published 11 days ago • 27

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Paper • 2609.26796 • Published 3 days ago • 15

New activity in IFM/K2-Horizon-32B 3 days ago

training cutoff

1

#3 opened 3 days ago by

khtsly

New activity in XingChen-AGI/Xing4.0-29B-A4B 4 days ago

training data knowledge cutoff

1

#10 opened 4 days ago by

khtsly

New activity in SHSLab/Step-5-Preview-BF16 4 days ago

Request: DOI

10

#1 opened 4 days ago by

win10

liked 2 models 4 days ago

SHSLab/Step-5-Preview-BF16

Image-Text-to-Text • 604B • Updated 4 days ago • 384 • 7

rene98c/Step-5-Preview-BF16

604B • Updated 5 days ago • 190 • 16

upvoted 3 papers 7 days ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 8 days ago • 108

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 8 days ago • 178

JEPA-Anything: Learning Predictive Models across Different Worlds

Paper • 2609.20800 • Published 8 days ago • 70

upvoted 3 papers 8 days ago

VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention

Paper • 2609.15810 • Published 11 days ago • 50

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Paper • 2609.18805 • Published 9 days ago • 62

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published 9 days ago • 79