XuHao Hu's picture

XuHao Hu

Foreshhh

·

AI & ML interests

NLP MM

Recent Activity

upvoted a paper about 7 hours ago

WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation

updated a collection about 23 hours ago

updated a collection about 23 hours ago

View all activity

Organizations

Collections 1

Papers 9

arxiv:2605.12481

arxiv:2604.04215

arxiv:2602.16855

arxiv:2510.08211

spaces 1

MD Judge Demo

models 2

Foreshhh/Qwen2-VL-7B-SafeRLHF

Visual Question Answering • 8B • Updated Dec 22, 2024 • 20 • 3

Foreshhh/Qwen2-VL-7B-VLGuard

Visual Question Answering • 8B • Updated Dec 16, 2024 • 20 • 1

datasets 2

Foreshhh/vlsbench

Viewer • Updated Aug 12, 2025 • 2.24k • 1.3k • 8

Foreshhh/BeaverTails-V

Viewer • Updated Mar 25, 2025 • 30.4k • 1.45k • 1