paper-with-me

홈 › Papers

Visual Attention Reasoning via Hierarchical Search and Self-Verification

2025-10-21 · Wei Cai, Jian Zhao, Yuchen Yuan, Tianle Zhang, Ming Zhu, Haichuan Tang, Xuelong Li arxiv

Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We propose Visual Attention Reasoning (VAR), a reinforcement learning framework that reformulates reasoning as a hierarchical search with self-verification. VAR enforces traceable evidence grounding by generating explicit bounding boxes, guided by a novel reward function combining geometric precision and semantic sufficiency. Furthermore, it replaces linear Chain-of-Thought with a tree-search policy capable of backtracking to correct logical errors. Theoretical analysis validates the framework's reliability, and extensive experiments demonstrate that VAR significantly outperforms state-of-the-art methods on complex hallucination and safety benchmarks.

📄 PDF Abstract BibTeX arXiv:2510.18619

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningVisual Grounding

Similar Papers 제목 키워드 기반

Local-to-Global Self-Attention in Vision Transformers

2021-07-10 · Jinpeng Li, Yichao Yan, Shengcai Liao, Xiaokang Yang 외

Transformers have demonstrated great potential in computer vision tasks. To avoid dense computations of self-attentions in high-resolution visual data, some recent Transformer models adopt a hierarchical design, where se…

image-classificationImage ClassificationSemantic Segmentation

Modulated Self-attention Convolutional Network for VQA

2019-10-08 · Jean-Benoit Delbrouck, Antoine Maiorca, Nathan Hubens, Stéphane Dupont

As new data-sets for real-world visual reasoning and compositional question answering are emerging, it might be needed to use the visual feature extraction as a end-to-end process during training. This small contribution…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Visual Reasoning

Self-supervised Hierarchical Visual Reasoning with World Model

2026-05-17 · Yuanfei Xu, Lin Liu, Wengang Zhou, Mingxiao Feng 외 arxiv

3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are essential in such settings. While existing …

Reinforcement LearningVisual Reasoning

PhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture

2023-06-26 · Mohit Vaishnav

We investigate the role of attention and memory in complex reasoning tasks. We analyze Transformer-based self-attention as a model and extend it with memory. By studying a synthetic visual reasoning test, we refine the t…

Visual ReasoningZero-shot Generalization

Hierarchical Denoising For Multi-Step Visual Reasoning

2026-07-16 · Zezhong Qian, Xiaowei Chi, Chak-Wing Mak, Tianze Zhou 외 arxiv

Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusio…

Visual ReasoningVideo Generation