小川陽太

david-mitchell's activity

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

upvoted a paper 1 day ago

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

Paper • 2605.14786 • Published 10 days ago • 2

upvoted 2 papers 2 days ago

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining

Paper • 2605.14747 • Published 10 days ago • 142

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Paper • 2605.20258 • Published 6 days ago • 29

upvoted a paper 4 days ago

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Paper • 2605.18401 • Published 6 days ago • 123

upvoted a paper 15 days ago

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

Paper • 2605.06130 • Published 17 days ago • 110

upvoted a paper 16 days ago

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

Paper • 2605.05185 • Published 18 days ago • 99

upvoted a paper 17 days ago

Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models

Paper • 2604.27124 • Published 25 days ago • 11

upvoted a paper about 1 month ago

Geometric coherence of single-cell CRISPR perturbations reveals regulatory architecture and predicts cellular stress

Paper • 2604.16642 • Published Apr 17 • 4

upvoted 2 papers about 2 months ago

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Paper • 2604.02721 • Published Apr 3 • 629

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Paper • 2603.26164 • Published Mar 27 • 364