Yao Zhang

ZYao720's activity

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

upvoted a paper 20 days ago

QuoteBench: How Matched Scores Can Hide Command-Path Failures

Paper • 2608.13547 • Published 30 days ago • 8

updated 4 models 5 months ago

ZYao720/WebArbiter-8B-Qwen3

Text Generation • 8B • Updated Apr 9 • 13

ZYao720/WebArbiter-4B-Qwen3

Text Generation • 4B • Updated Apr 9 • 12 • 1

ZYao720/WebArbiter-7B

Text Generation • 8B • Updated Apr 9 • 93 • 1

ZYao720/WebArbiter-3B

Text Generation • 3B • Updated Apr 9 • 16

updated 2 datasets 5 months ago

ZYao720/WebArbiter-Data

Viewer • Updated Apr 9 • 9.64k • 36 • 2

ZYao720/WEBPRMBENCH

Viewer • Updated Apr 9 • 4.6k • 47 • 2

updated 3 collections 5 months ago

WebArbiter - Datasets

Collection

Benchmark, training data, and search trajectories for WebArbiter. ICLR 2026. • 3 items • Updated Apr 9

WebArbiter - Models

Collection

WebArbiter process reward models for web agents. Reasoning distillation + RL. ICLR 2026. • 4 items • Updated Apr 9

WebArbiter

Collection

Reasoning Process Reward Model for Web Agents. Models, data, and WebPRMBench. ICLR 2026. • 8 items • Updated Apr 9

updated a dataset 5 months ago

ZYao720/WebArbiter-Trajectories

Updated Apr 8 • 10

updated a collection 5 months ago

WebArbiter

Collection

Reasoning Process Reward Model for Web Agents. Models, data, and WebPRMBench. ICLR 2026. • 8 items • Updated Apr 9

published a dataset 5 months ago

ZYao720/WebArbiter-Trajectories

Updated Apr 8 • 10