Weida Wang

weidawang's activity

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

upvoted 2 papers 4 days ago

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Paper • 2609.32353 • Published 7 days ago • 8

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Paper • 2609.34972 • Published 5 days ago • 30

upvoted 3 papers 17 days ago

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

Paper • 2609.02749 • Published Sep 2 • 407

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 19 days ago • 251

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published 19 days ago • 434

upvoted 2 papers about 1 month ago

FrontierChallenge: Evaluating Scientific Workflow Completion

Paper • 2608.24979 • Published Aug 25 • 152

Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning

Paper • 2604.16890 • Published Apr 18 • 2

upvoted 3 papers 3 months ago

Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

Paper • 2607.07708 • Published Jul 8 • 88

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 84

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

Paper • 2606.24530 • Published Jun 23 • 67

upvoted an article 4 months ago

view article

Article

PhysicsIntern: from an Autonomous Benchmark-runner to a Research Sidekick

• 

dlouapre

•

Jun 11

• 7

upvoted 2 papers 4 months ago

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Paper • 2606.07591 • Published May 28 • 106

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

Paper • 2605.31264 • Published May 29 • 130

upvoted 3 papers 5 months ago

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Paper • 2605.20025 • Published May 19 • 90

Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning

Paper • 2605.06326 • Published May 7 • 26

δ-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published May 12 • 133

upvoted 3 papers 6 months ago

PRBench: End-to-end Paper Reproduction in Physics Research

Paper • 2603.27646 • Published Mar 29 • 25

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published Mar 26 • 132

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Paper • 2603.21065 • Published Mar 22 • 80

upvoted a paper 7 months ago

Memento-Skills: Let Agents Design Agents

Paper • 2603.18743 • Published Mar 19 • 59