Bag of Tricks for Subverting Reasoning-based Safety Guardrails Paper • 2510.11570 • Published about 1 month ago • 1
True Multimodal In-Context Learning Needs Attention to the Visual Context Paper • 2507.15807 • Published Jul 21 • 1
SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence Paper • 2506.15672 • Published Jun 18 • 15
Visual Question Decomposition on Multimodal Large Language Models Paper • 2409.19339 • Published Sep 28, 2024 • 9
Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images Paper • 2402.14899 • Published Feb 22, 2024 • 1