AIM-CoT enhances interleaved multimodal chain-of-thought reasoning by adding context-enhanced attention generation, active visual probing via information foraging, and dynamic attention-shift triggering.
Xuanyu Lei, Zonghan Yang, Xinrui Chen, Peng Li, and Yang Liu
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning
AIM-CoT enhances interleaved multimodal chain-of-thought reasoning by adding context-enhanced attention generation, active visual probing via information foraging, and dynamic attention-shift triggering.