khtsly

khtsly's activity

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

commented a paper 3 days ago

Multi-Head Attention Residuals

Paper • 2607.27230 • Published 13 days ago • 8 •

3

upvoted a paper 3 days ago

Multi-Head Attention Residuals

Paper • 2607.27230 • Published 13 days ago • 8

commented a paper 5 days ago

xHC: Expanded Hyper-Connections

Paper • 2607.14530 • Published 19 days ago • 56 •

3

commented a paper 6 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 8 days ago • 444 •

9

upvoted a paper 6 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 8 days ago • 444

New activity in moonshotai/Kimi-K3 7 days ago

Kimi K3 Air? Flash???

👍 1

2

#74 opened 7 days ago by

Kosh69

liked a model 7 days ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 7 days ago • 968k • • 9.79k

liked a dataset 7 days ago

HuggingFaceCode/stack-v3-train

Viewer • Updated about 1 hour ago • 173M • 136k • 291

upvoted 2 papers 14 days ago

Understanding Reasoning from Pretraining to Post-Training

Paper • 2607.16097 • Published 18 days ago • 28

xHC: Expanded Hyper-Connections

Paper • 2607.14530 • Published 19 days ago • 56

upvoted a paper 15 days ago

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 194

upvoted 2 papers 26 days ago

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

Paper • 2607.05147 • Published 29 days ago • 41

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 84

upvoted a paper 28 days ago

Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming

Paper • 2606.31227 • Published Jun 30 • 14

upvoted 5 papers about 1 month ago

Multi-Block Diffusion Language Models

Paper • 2606.29215 • Published Jun 30 • 42

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

Paper • 2606.32032 • Published Jun 30 • 29

HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization

Paper • 2606.20097 • Published Jun 18 • 19

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published Jun 20 • 26

Looped World Models

Paper • 2606.18208 • Published Jun 16 • 484

upvoted a paper about 2 months ago

Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents

Paper • 2606.06036 • Published Jun 4 • 77