3 papers
cs.CV2026
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
Lianyu Hu, Shengqian Qin, Zeqin Liao +4
Chain-of-thought (CoT) reasoning has enabled multi-modal large language models (MLLMs) to tackle complex visual reasoning tasks by generating explicit intermediate reasoning steps…
cs.MA2026
MetaCrit: A Critical Thinking Framework for Self-Regulated LLM Reasoning
Xinmeng Hou, Ziting Chang, Zhouquan Lu +5
Large language models (LLMs) fail on over one-third of multi-hop questions with counterfactual premises and remain vulnerable to adversarial prompts that trigger biased or factuall…
cs.CV2025
OBJVanish: Physically Realizable Text-to-3D Adv. Generation of LiDAR-Invisible Objects
Bing Li, Wuqi Wang, Yanan Zhang +6
LiDAR-based 3D object detectors are fundamental to autonomous driving, where failing to detect objects poses severe safety risks. Developing effective 3D adversarial attacks is ess…