paper-with-me

Papers

AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning

2025-09-30 · Xiping Li, Jianghong Ma arxiv

Interleaved-Modal Chain-of-Thought (I-MCoT) advances vision-language reasoning, such as Visual Question Answering (VQA). This paradigm integrates specially selected visual evidence from the input image into the context of Vision-Language Models (VLMs), enabling them to ground their reasoning logic in these details. Accordingly, the efficacy of an I-MCoT framework relies on identifying what to see (evidence selection) and when to see it (triggering of insertions). However, existing methods fall short in both aspects. First, for selection, they rely on attention signals, which are unreliable -- particularly under severe granularity imbalance between the brief textual query and the informative image. Second, for triggering, they adopt static triggers, which fail to capture the VLMs' dynamic needs for visual evidence. To this end, we propose a novel I-MCoT framework, Active Information-driven Multi-modal Chain-of-Thought (AIM-CoT), which aims to improve both evidence selection and insertion triggering via: (1) Context-enhanced Attention-map Generation (CAG) to mitigate granularity imbalance via textual context enhancement; (2) Active Visual Probing (AVP) to proactively select the most informative evidence via an information foraging process; and (3) Dynamic Attention-shift Trigger (DAT) to precisely activate insertions when VLM's attention shifts from text to visual context. Experiments across three benchmarks and four backbones demonstrate AIM-CoT's consistent superiority. Our code is available at https://anonymous.4open.science/r/AIMCoT.

📄 PDF Abstract BibTeX arXiv:2509.25699

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question Answering

Similar Papers 제목 키워드 기반

Chain of Questions: Guiding Multimodal Curiosity in Language Models

2025-08-06 · Nima Iji, Kia Dashtipour arxiv

Reasoning capabilities in large language models (LLMs) have substantially advanced through methods such as chain-of-thought and explicit step-by-step explanations. However, these improvements have not yet fully transitio…

Response Generation

Interleaved-Modal Chain-of-Thought

2024-11-29 · CVPR 2025 1 · Jun Gao, Yongqi Li, Ziqiang Cao, Wenjie Li

Chain-of-Thought (CoT) prompting elicits large language models (LLMs) to produce a series of intermediate reasoning steps before arriving at the final answer. However, when transitioning to vision-language models (VLMs),…

BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards

2026-02-20 · Yiran Yang, Zhaowei Liu, Yuan Yuan, Yukun Song 외 arxiv

Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framewo…

Reinforcement Learning

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

2026-02-05 · Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao 외 arxiv

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely lang…

Reinforcement Learning

Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts

2026-01-07 · Zhihao Zhu, Jiafeng Liang, Shixin Jiang, Jinlan Fu 외 arxiv

Large Multimodal Models (LMMs) have demonstrated impressive capabilities in video reasoning via Chain-of-Thought (CoT). However, the robustness of their reasoning chains remains questionable. In this paper, we identify a…