Lane Sun

lanesun's activity

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

upvoted a paper 12 days ago

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

Paper • 2609.24983 • Published 14 days ago • 55

upvoted a collection 16 days ago

Deepseek Papers

Collection

Deepseek papers collection • 34 items • Updated 12 days ago • 373

upvoted a paper 16 days ago

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

Paper • 2609.19969 • Published 18 days ago • 218

upvoted an article 3 months ago

view article

Article

Distillation in 2026 (so far): which frontier models use it and how

• 

sergiopaniego

•

Jul 8

• 22

upvoted a collection 4 months ago

💧 LFM2.5

Collection

Collection of post-trained and base LFM2.5 models. • 16 items • Updated Aug 4 • 230

upvoted 3 papers 4 months ago

Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

Paper • 2606.03979 • Published Jun 2 • 29

ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence

Paper • 2605.26340 • Published May 25 • 36

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

Paper • 2605.25624 • Published May 25 • 34

upvoted a paper 7 months ago

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference

Paper • 2602.21548 • Published Feb 25 • 57

upvoted an article 8 months ago

view article

Article

One Year Since the “DeepSeek Moment”

• 

huggingface

•

Jan 20

• 64