XuHao Hu

Foreshhh's activity

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

authored 4 papers 27 days ago

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks

Paper • 2506.16402 • Published Jun 19 • 1

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law

Paper • 2507.18576 • Published Jul 24 • 6

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report

Paper • 2507.16534 • Published Jul 22 • 7

Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step

Paper • 2509.23924 • Published Sep 28 • 7

authored a paper 28 days ago

LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

Paper • 2510.08211 • Published 28 days ago • 22

authored a paper 8 months ago

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

Paper • 2501.12612 • Published Jan 22

authored a paper over 1 year ago

SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

Paper • 2402.05044 • Published Feb 7, 2024 • 2