PulseAugur
EN
LIVE 00:00:36

New VQA benchmarks and methods tackle knowledge, adaptation, and grounding

By PulseAugur Editorial · [8 sources] ·

Researchers have introduced several new benchmarks and methods for Visual Question Answering (VQA) systems. HyLoVQA proposes a dynamic hypernetwork-generated low-rank adaptation technique for continual VQA, improving adaptation to new tasks and objects. WikiVQABench offers a knowledge-grounded VQA benchmark using Wikipedia and Wikidata, designed to test models requiring external knowledge. Additionally, UCSF-PDGM-VQA focuses on brain tumor MRI interpretation, highlighting current VLM limitations in clinical settings, while RoboSurg-VQA addresses surgical segmentation-aware VQA, and VISTAQA benchmarks joint answer correctness and pixel-level evidence grounding. AI

IMPACT These new benchmarks and adaptation techniques aim to improve the reliability and capabilities of Vision-Language Models in complex, real-world scenarios.

RANK_REASON Multiple research papers introducing new benchmarks and methods for Visual Question Answering.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 8 sources. How we write summaries →

New VQA benchmarks and methods tackle knowledge, adaptation, and grounding

COVERAGE [8]

  1. arXiv cs.CL TIER_1 English(EN) · Yiran Wang, Chenyi Xiong, Ziyue Qin, Miao Zhang, Kui Xiao, Zhifei Li ·

    HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering

    arXiv:2605.22035v1 Announce Type: cross Abstract: Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge. Most prior methods adapt by updating a largely shared parameter set. This ofte…

  2. arXiv cs.AI TIER_1 English(EN) · Basel Shbita, Pengyuan Li, Anna Lisa Gentile ·

    WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata

    arXiv:2605.21479v1 Announce Type: cross Abstract: Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observa…

  3. arXiv cs.AI TIER_1 English(EN) · Shiv Ghosh, Junayd Lateef, Chih-Hua Liu, Yannan Yu, Andreas M. Rauschecker, Madhumita Sushil ·

    UCSF-PDGM-VQA: Visual Question Answering dataset for brain tumor MRI interpretation

    arXiv:2605.17140v2 Announce Type: replace-cross Abstract: Brain tumor diagnosis is largely dependent on Magnetic Resonance Imaging (MRI) evaluation, which requires radiologists to synthesize thousands of images across multiple 3D sequences and longitudinal studies. This process r…

  4. arXiv cs.CL TIER_1 English(EN) · Zhifei Li ·

    HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering

    Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge. Most prior methods adapt by updating a largely shared parameter set. This often leads to cross-level task interference, hinderin…

  5. arXiv cs.AI TIER_1 English(EN) · Anna Lisa Gentile ·

    WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata

    Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observable in the image to answer correctly. We introduce…

  6. Hugging Face Daily Papers TIER_1 English(EN) ·

    WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata

    Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observable in the image to answer correctly. We introduce…

  7. arXiv cs.CV TIER_1 English(EN) · Chengyi Zhang, Zi Ye, Ziyang Wang ·

    RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answering

    arXiv:2605.23068v1 Announce Type: new Abstract: Reliable visual understanding in robot-assisted and minimally invasive surgery (RMIS/MIS) demands more than accurate masks: in clinical practice, clinicians pose language-like questions about procedural context, visibility, artefact…

  8. arXiv cs.CV TIER_1 English(EN) · Krzysztof Czarnecki ·

    VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence

    Establishing a clear link between model predictions and the visual evidence that supports them is critical for transparency and reliability in multimodal reasoning, yet current multimodal large language model (MLLM) evaluations do not explicitly enforce this alignment. Existing b…

RELATED ENTITIES

RELATED TOPICS