Blanc Swan

blancsw's activity

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

upvoted a paper 2 days ago

H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache

Paper • 2609.24197 • Published Sep 21 • 1

upvoted an article 16 days ago

view article

Article

Build specialized multimodal models with LFM3

• 

LiquidAI

•

16 days ago

• 111

upvoted a paper 16 days ago

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published Oct 13 • 140

upvoted 3 papers 22 days ago

Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation

Paper • 2610.14162 • Published Oct 9 • 32

LEV: Thinking Fast and Deep with Looped Decision Models

Paper • 2610.20951 • Published about 1 month ago • 72

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse

Paper • 2608.03893 • Published Aug 4 • 3

upvoted 2 papers about 1 month ago

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

Paper • 2609.36484 • Published Sep 29 • 168

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

Paper • 2609.38721 • Published Sep 30 • 134

upvoted 3 papers about 2 months ago

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

Paper • 2609.19969 • Published Sep 17 • 208

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 76

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

Paper • 2609.08183 • Published Sep 8 • 70

upvoted 5 papers 2 months ago

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

Paper • 2609.02749 • Published Sep 2 • 148

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published Sep 2 • 78

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

Paper • 2608.31046 • Published Aug 31 • 85

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

Paper • 2608.30320 • Published Aug 31 • 62

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 153

upvoted 3 papers 3 months ago

MiniMax Sparse Attention

Paper • 2606.13392 • Published Jun 11 • 171

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 224

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published Mar 12 • 68

upvoted a paper 4 months ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 526