Visual Attention Reasoning via Hierarchical Search and Self-Verification
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningVisual GroundingSimilar Papers 제목 키워드 기반
Local-to-Global Self-Attention in Vision Transformers
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 SegmentationModulated Self-attention Convolutional Network for VQA
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 ReasoningSelf-supervised Hierarchical Visual Reasoning with World Model
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 ReasoningPhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture
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 GeneralizationHierarchical Denoising For Multi-Step Visual Reasoning
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