{"ID":2873942,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.05669","arxiv_id":"2509.05669","title":"Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance","abstract":"Current Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) excel in single-turn tasks but face significant challenges in multi-turn interactions requiring deep contextual understanding and complex visual reasoning, often leading to fragmented reasoning, context loss, and hallucinations. To address these limitations, we propose Context-Aware Multi-Turn Visual Reasoning (CAMVR), a novel framework designed to empower LVLMs with robust and coherent multi-turn visual-textual inference capabilities. CAMVR introduces two key innovations: a Visual-Textual Context Memory Unit (VCMU), a dynamic read-write memory network that stores and manages critical visual features, textual semantic representations, and their cross-modal correspondences from each interaction turn; and an Adaptive Visual Focus Guidance (AVFG) mechanism, which leverages the VCMU's context to dynamically adjust the visual encoder's attention to contextually relevant image regions. Our multi-level reasoning integration strategy ensures that response generation is deeply coherent with both current inputs and accumulated historical context. Extensive experiments on challenging datasets, including VisDial, an adapted A-OKVQA, and our novel Multi-Turn Instruction Following (MTIF) dataset, demonstrate that CAMVR consistently achieves state-of-the-art performance.","short_abstract":"Current Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) excel in single-turn tasks but face significant challenges in multi-turn interactions requiring deep contextual understanding and complex visual reasoning, often leading to fragmented reasoning, context loss, and hallucinations. To address th...","url_abs":"https://arxiv.org/abs/2509.05669","url_pdf":"https://arxiv.org/pdf/2509.05669v1","authors":"[\"Weijie Shen\",\"Xinrui Wang\",\"Yuanqi Nie\",\"Apiradee Boonmee\"]","published":"2025-09-06T10:14:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}