Visual Question Answering (VQA)

Visual Question Answering (VQA) is a benchmark that evaluates the ability of models to answer questions about images, integrating visual and textual understanding.

Papers using Visual Question Answering (VQA) (17)

Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding2026Cross-Modal Attention Guided Unlearning in Vision-Language Models2025Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs2025Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning2025Towards Resource-efficient Multimodal Intelligence: Learned Routing Among Specialized Expert Models2025Do Large Vision-language Models Distinguish Between The Actual And Apparent Features Of Illusions?2025Adaptive Token Boundaries: Integrating Human Chunking Mechanisms into Multimodal LLMs2025Large-Scale Adversarial Training for Vision-and-Language Representation Learning2020 · 287 citesHow Much Can CLIP Benefit Vision-and-Language Tasks?2021 · 153 citesCross-Modality Relevance for Reasoning on Language and Vision2020 · 33 citesCLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks2022 · 19 citesLarge Language Models are Visual Reasoning Coordinators2023 · 14 citesMultimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks2022 · 8 citesUncertainty-Aware Evaluation for Vision-Language Models2024 · 2 citesLarge-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline2019 · 1 citesCAVL: Learning Contrastive and Adaptive Representations of Vision and Language2023 · 1 citesBoth Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM2024