Boyu Gou

BoyuNLP's activity

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

New activity in osunlp/Mind2Web-2 37 minutes ago

Describe the sequential scoring of nyc_sport_event's events (dev set)

#8 opened 37 minutes ago by

BoyuNLP

New activity in osunlp/Mind2Web-2 about 2 hours ago

Fix scoring bugs in 11 evaluation scripts

#7 opened about 2 hours ago by

BoyuNLP

New activity in osunlp/Mind2Web-2 about 4 hours ago

Fix evaluation-script crashes on incomplete answers

#6 opened about 4 hours ago by

BoyuNLP

New activity in ChilleD/WebHarbor 3 months ago

Add drugs_com.tar.gz (seed DB + pill images for the drugs_com WebHarbor mirror)

2

#39 opened 3 months ago by

BoyuNLP

authored a paper 3 months ago

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Paper • 2606.02540 • Published Jun 1 • 10

authored 2 papers 4 months ago

Beyond Clicking:A Step Towards Generalist GUI Grounding via Text Dragging

Paper • 2601.06031 • Published Nov 7, 2025

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Paper • 2605.24218 • Published May 22 • 45

upvoted a paper 4 months ago

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Paper • 2605.24218 • Published May 22 • 45

New activity in ChilleD/WebHarbor 4 months ago

Upload drugs_com.tar.gz with huggingface_hub

2

#13 opened 4 months ago by

BoyuNLP

Upload drugs_com.tar.gz with huggingface_hub

#12 opened 4 months ago by

BoyuNLP

New activity in osunlp/UGround-V1-2B 7 months ago

Clarification on osunlp/UGround-V1-2B training origin

2

#2 opened 7 months ago by

dqdw

liked a dataset 7 months ago

osunlp/MisActBench

Updated Feb 18 • 73 • 2

authored a paper 11 months ago

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

Paper • 2510.24702 • Published Oct 28, 2025 • 32

liked a dataset 11 months ago

neulab/agent-data-collection

Preview • Updated Mar 9 • 9.66k • 115

upvoted a paper 11 months ago

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

Paper • 2510.24702 • Published Oct 28, 2025 • 32

New activity in osunlp/Mind2Web-2 11 months ago

TODO: Eval Script Optimization

#5 opened 11 months ago by

BoyuNLP

re-2.0

#4 opened 11 months ago by

BoyuNLP

liked a dataset 11 months ago

osunlp/Mind2Web-2

Viewer • Updated Dec 14, 2025 • 130 • 94 • 16

authored a paper 12 months ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 257

upvoted a paper 12 months ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 257