Blanc Swan

blancsw's activity

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

upvoted 2 papers about 3 hours ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 3 days ago • 270

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 2 days ago • 186

upvoted a paper 13 days ago

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

Paper • 2609.19969 • Published 15 days ago • 191

upvoted 2 papers 18 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 485

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 24 days ago • 327

upvoted a paper 23 days ago

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Paper • 2609.02749 • Published 30 days ago • 407

upvoted a paper 26 days ago

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published 30 days ago • 79

upvoted a paper 28 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published Aug 31 • 97

upvoted 2 papers 30 days ago

On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

Paper • 2608.30320 • Published Aug 31 • 63

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published about 1 month ago • 494

upvoted 3 papers about 2 months ago

MiniMax Sparse Attention

Paper • 2606.13392 • Published Jun 11 • 169

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 221

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published Mar 12 • 69

upvoted a paper 2 months ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 526

upvoted an article 2 months ago

view article

Article

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

• 

ResterChed

•

Jul 17

• 197

upvoted an article 3 months ago

view article

Article

Native-speed vLLM transformers modeling backend

• 
• 

hmellor, lysandre

•

Jul 8

• 77

upvoted 2 papers 3 months ago

Orca: The World is in Your Mind

Paper • 2606.30534 • Published Jun 29 • 508

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 100

upvoted a collection 6 months ago

Qwen3.6

Collection

4 items • Updated Apr 22 • 501

upvoted a paper 6 months ago

LightRAG: Simple and Fast Retrieval-Augmented Generation

Paper • 2410.05779 • Published Oct 8, 2024 • 43