arXiv:2606. 05535v1 Announce Type: cross Abstract: Medical visual question answering (Med-VQA) has strong potential for clinical decision support by enabling AI models to interpret medical images and answer clinically relevant queries.
arXiv:2609.35942v1 Announce Type: new Abstract: Recent work in visual question answering has shown that vision-language models can exhibit strong reasoning capabilities by translating visual inputs i...
arXiv:2605. 29588v2 Announce Type: replace-cross Abstract: Decoding visual content from fMRI signals recorded while a person views images, and specifically answering questions about the seen images, is a long-standing challenge.
The paper introduces a new training framework for Visual Question Answering that leverages counterfactual contrastive learning to mitigate language bias and improve out‑of‑distribution generalization. It comprises a three‑stage curriculum for stable optimization, an enhanced Batch‑Contrastive loss for discriminative feature learning, and two regularizers—Answer‑Contrastive and Gradient‑Discrepancy—to refine predictions and enforce causal visual grounding. The resulting model attains 61.64% accuracy on the bias‑sensitive VQA‑CP v2 benchmark while maintaining 62.80% on the standard VQA v2 dataset, achieving a small generalization gap of 1.16%.
arXiv:2610.01180v1 Announce Type: new Abstract: Despite the strong performance of Vision-Language Models (VLMs) on a wide range of visual question answering (VQA) tasks, these models consistently str...
The paper introduces Self-RefineVQA, a training‑free, inference‑time framework that lets a single Vision‑Language Model iteratively generate, critique, and refine its own answers for table visual question answering. By forming a closed self‑feedback loop guided by prompts, the method corrects common reasoning errors such as spatial misalignment and logical hallucinations without requiring additional labeled data or model updates. Experiments on tabular VQA benchmarks show consistent accuracy gains across monolingual and cross‑lingual settings, especially for lightweight models, while keeping inference cost linear and eliminating the need for expensive supervised fine‑tuning.
arXiv:2602. 14065v2 Announce Type: replace Abstract: Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval.
Document Visual Question Answering (DocVQA) presents a complex multimodal challenge, requiring models to exploit visual, textual, and layout information from documents. Although Vision-Language Models (VLMs) have shown remarkable performance in text-vision tasks, their robustness and transferability to different document domains remains underexplored.
This article presents a Visual Question Answering (VQA) model tailored for nondestructive evaluation (NDE) image analysis. The system combines a ResNet‑50 image encoder with a GPT‑2 language generator, allowing inspectors to ask targeted questions such as "Is there a crack?" or "Where is the defect located?" and receive precise answers. By facilitating direct question‑and‑answer interactions, the VQA model aims to improve inspection efficiency, reduce errors, and enhance usability in field scenarios.
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:2607. 07179v1 Announce Type: cross Abstract: Document Visual Question Answering (DocVQA) presents a complex multimodal challenge, requiring models to exploit visual, textual, and layout information from documents.
The paper investigates how to best integrate large language model (LLM) guidance into visual question answering (VQA) systems. By prompting the 70‑billion‑parameter Llama 3.3 model to identify visual concepts, distractors, and external facts for each question, the authors inject this guidance into a frozen Vision Transformer (ViT) and a T5 text‑to‑text model via two methods: decision‑level late fusion and attention‑matrix injection. On the OK‑VQA benchmark, the shallow late‑fusion approach outperforms the deeper attention injection, achieving 39.4% exact match versus 31.8%, and a paraphrasing pipeline further expands the training set tenfold, indicating that the depth of integration should match the data regime.