arXiv:2609.05518v1 Announce Type: cross Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, m...
arXiv:2608. 15056v1 Announce Type: new Abstract: Multimodal retrieval-augmented generation (RAG) systems often rely on long unstructured contexts or aggressively expanded evidence graphs, which can introduce noisy evidence, weaken multi-hop reasoning, and increase unsupported generation.
arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visua...
arXiv:2607. 22643v1 Announce Type: new Abstract: Multimodal retrieval-augmented generation (mRAG) aims to answer image-text queries with external knowledge, but most existing systems still retrieve directly from raw multimodal input over a flat evidence space.
VISPATH is a visual‑intent‑guided path reasoning framework designed for multimodal knowledge graph question answering (MM‑KGQA). It first identifies a reliable starting entity by fusing multimodal grounding with graph‑structural cues, then iteratively discovers and refines reasoning paths using hop‑specific multimodal intent and a reasoning‑chain pruning step. The framework is evaluated on the newly introduced VISPATH‑Bench, which tests two‑to‑four‑hop reasoning, and demonstrates consistent improvements over strong baselines, even surpassing GPT‑5.4 when using GPT‑4o as the backbone.
SLVR (Structured Latent Visual Reasoning) is a training framework that blends explicit chain-of-thought with latent reasoning for multimodal large language models. It organizes reasoning into typed latent stages—planning, grounding, evidence selection, and integration—each supervised by corresponding signals such as plans, bounding boxes, visual evidence, and final rationales. Built on Qwen2.5‑VL‑7B, SLVR consistently improves performance on multimodal reasoning benchmarks, achieving significant gains on MMVP, BLINK Relation, V*, MathVista, and ChartQA.
CLIMB is a training‑free inference‑time framework for multimodal retrieval‑augmented generation. It builds a compact complementary evidence pool using an MMR‑style objective that balances relevance and redundancy, then refines answers with a confidence‑controlled critic that scores relevance, specificity, and cross‑modal alignment. The method stops refinement when confidence no longer rises, improving performance on Encyclopedic‑VQA and InfoSeek without altering the retriever or language model.
DocHop is a new benchmark that tests multimodal large language models on integrated chart‑context reasoning within document‑style images. The benchmark presents narrative text that imposes multi‑step compositional constraints, while charts supply the data needed to answer questions grounded in semantic reference labels. It contains 2,074 examples across six task categories, generated via a stochastic logic‑first pipeline that controls reasoning depth and visual density, and shows a large performance gap between humans (over 90% accuracy) and the best models (62.83%).
arXiv:2608.21431v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering aims to answer questions about an image by integrating external knowledge with visual and textual information...
arXiv:2604. 01280v2 Announce Type: replace-cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) requires Multimodal Large Language Models (MLLMs) to identify and combine fine-grained visual cues with retrieved textual evidence.
arXiv:2609.16795v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved...
arXiv:2607. 16208v1 Announce Type: new Abstract: Graph-grounded multimodal question answering organizes text, tables, and images in a structured evidence graph, yet end-to-end accuracy depends on which multimodal assets are ranked highly enough to enter downstream reasoning; for graph-linked images, single-vector bi-encoder similarity can discard patch- and token-level structure needed for fine-grained alignment.