Dawei Liu

davidliuk's activity

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

upvoted a paper about 12 hours ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 4 days ago • 113

upvoted a paper 7 days ago

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

Paper • 2609.22086 • Published 11 days ago • 34

upvoted a paper 21 days ago

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published 29 days ago • 174

upvoted a paper 3 months ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published Jul 9 • 77

upvoted a paper 5 months ago

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks

Paper • 2604.20987 • Published Apr 22 • 22

upvoted a collection 5 months ago

Gemma 4

Collection

Our most intelligent open models to date • 16 items • Updated Aug 20 • 1.15k

upvoted 2 papers 6 months ago

Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Paper • 2604.05333 • Published Apr 7 • 22

Towards a Medical AI Scientist

Paper • 2603.28589 • Published Mar 30 • 91

upvoted a paper 7 months ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published Mar 10 • 55

upvoted a paper 8 months ago

LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation

Paper • 2602.10367 • Published Feb 10 • 13

upvoted a paper about 1 year ago

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

Paper • 2507.11097 • Published Jul 15, 2025 • 65