When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
Paper
• 2602.08235 • Published
Yuting Ning
nnnyt
AI & ML interests
None yet
Recent Activity
authored
a paper
6 days ago
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents new activity
6 days ago
osunlp/MisActBench:Add image-text-to-text task category to metadata authored
a paper
13 days ago
When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents Organizations
authored a paper 6 days ago
authored a paper 13 days ago
submitted a paper to Daily Papers 13 days ago
authored a paper 5 months ago
authored a paper 8 months ago
authored 3 papers over 1 year ago
In Search of the Long-Tail: Systematic Generation of Long-Tail Knowledge via Logical Rule Guided Search
Paper
• 2311.07237 • Published
ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
Paper
• 2410.05080 • Published
• 21
Pandora: Towards General World Model with Natural Language Actions and Video States
Paper
• 2406.09455 • Published
• 16