Chengxuan Tao

CXTao's activity

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

upvoted a paper about 10 hours ago

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

Paper • 2610.32285 • Published 6 days ago • 294

upvoted 2 papers 3 days ago

Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models

Paper • 2610.25100 • Published 11 days ago • 61

VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift

Paper • 2610.30090 • Published 8 days ago • 12

upvoted a paper 5 days ago

Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?

Paper • 2610.27592 • Published 9 days ago • 27

upvoted 2 papers 7 days ago

Self-Evaluating Recursive Agents

Paper • 2610.04902 • Published 25 days ago • 17

PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews

Paper • 2610.21046 • Published 14 days ago • 48

upvoted a paper 9 days ago

Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance

Paper • 2610.20220 • Published 15 days ago • 13

upvoted 2 papers 10 days ago

Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents

Paper • 2610.20344 • Published 15 days ago • 63

Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding

Paper • 2610.16118 • Published 17 days ago • 21