UnifiedAttack: Evaluating the Safety of Large Multimodal Models in Synergistic Harmful Image-Text Generation
Paper • 2610.00341 • Published • 1
Jialin Guo
GUALIN
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimization authored a paper 1 day ago
UnifiedAttack: Evaluating the Safety of Large Multimodal Models in Synergistic Harmful Image-Text Generation authored a paper 1 day ago
VideoEvolve: Evolving Agent Harnesses for Video Temporal GroundingOrganizations
None yet
upvoted 4
papers 1 day ago
VideoEvolve: Evolving Agent Harnesses for Video Temporal Grounding
Paper • 2610.01766 • Published • 1
Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimization
Paper • 2607.21619 • Published • 1
Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution
Paper • 2609.37950 • Published • 2