Dehai Min

ZhishanQ's activity

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

liked a dataset 3 days ago

yifannnwu/SWE-Together

Viewer • Updated Jul 7 • 109 • 312 • 1

upvoted a paper 3 days ago

SWE-Together: Evaluating Coding Agents in Interactive User Sessions

Paper • 2606.29957 • Published Jun 29 • 15

upvoted a paper 9 days ago

From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models

Paper • 2610.04139 • Published Oct 2 • 10

authored a paper 15 days ago

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published Sep 27 • 62

upvoted a paper 16 days ago

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

Paper • 2610.28763 • Published 18 days ago • 18

liked a dataset 16 days ago

gianniiii/planetarium-floor-tile-corrected

Viewer • Updated 23 days ago • 6.17k • 122 • 1

upvoted 2 papers 19 days ago

T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration

Paper • 2605.29054 • Published 24 days ago • 8

LEV: Thinking Fast and Deep with Looped Decision Models

Paper • 2610.20951 • Published 24 days ago • 72

upvoted a paper 29 days ago

Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight

Paper • 2610.08077 • Published Oct 6 • 165

upvoted 6 papers about 1 month ago

ALoDLM: Adaptively Looped Diffusion Language Models

Paper • 2610.04198 • Published Oct 3 • 68

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published Oct 1 • 24

X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization

Paper • 2609.32993 • Published Sep 26 • 53

TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent

Paper • 2609.27277 • Published Sep 23 • 28

LastOPD: Taming Collapse in Latent On-Policy Distillation

Paper • 2609.28845 • Published Sep 23 • 25

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published Sep 27 • 62

submitted a paper to Daily Papers about 1 month ago

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published Sep 27 • 62

upvoted a paper about 2 months ago

RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments

Paper • 2609.15364 • Published Sep 14 • 90

upvoted a paper 3 months ago

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Paper • 2608.06867 • Published Aug 7 • 90

upvoted an article 3 months ago

view article

Article

FineBooks: are open OCR models good enough to unlock historical knowledge?

• 

finebooks

•

Aug 10

• 27

upvoted a paper 3 months ago

Weak-to-Strong On-Policy Distillation

Paper • 2607.26246 • Published Jul 28 • 58