Yuming Yang

Umean

·

UmeanNever

AI & ML interests

NLP

Recent Activity

authored a paper 14 days ago

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments

updated a dataset 2 months ago

upvoted a paper 3 months ago

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

View all activity

Organizations

Papers 15

arxiv:2607.05174

arxiv:2601.14249

arxiv:2512.06726

arxiv:2509.16596

models 2

Umean/B2NER-Internlm2.5-7B-LoRA

Updated Jun 10, 2025 • 14 • 3

Umean/B2NER-Internlm2-20B-LoRA

Updated Jun 10, 2025 • 13 • 2

datasets 2

Umean/RSR_data

Preview • Updated Jul 1 • 426 • 3

Umean/B2NERD

Updated Jun 10, 2025 • 72 • 4