Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models
Paper
• 2601.12042 • Published
• 2
zhang
plll123
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 days ago
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning upvoted a paper 4 days ago
GLM-5: from Vibe Coding to Agentic Engineering upvoted an article 23 days ago
Character-Level Perturbations Disrupt LLM Watermarks Organizations
None yet
authored a paper 27 days ago
submitted a paper to Daily Papers 27 days ago