VQA

The VQA (Visual Question Answering) dataset contains images paired with questions and answers, and it is used to evaluate the ability of models to understand and reason about visual content in conjunction with natural language queries.

Papers using VQA (49)

Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence2026Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning2026EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State Detectors2026AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning2026DOSE: Data Selection for Multi-Modal LLMs via Off-the-Shelf Models2026RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understanding2026DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models2026Parallel In-context Learning for Large Vision Language Models2026Hidden Clones: Exposing and Fixing Family Bias in Vision-Language Model Ensembles2026N\"uwa: Mending the Spatial Integrity Torn by VLM Token Pruning2026VOILA: Value-of-Information Guided Fidelity Selection for Cost-Aware Multimodal Question Answering2026GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models2026Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs2026HybridToken-VLM: Hybrid Token Compression for Vision-Language Models2025Efficient Vision-Language Reasoning via Adaptive Token Pruning2025OMEGA: Optimized Multimodal Position Encoding Index Derivation with Global Adaptive Scaling for Vision-Language Models2025Draft and Refine with Visual Experts2025Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling2025Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering2025AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors2025MV-CoRe: Multimodal Visual-Conceptual Reasoning for Complex Visual Question Answering2025INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling2025From Pixels And Words To Waves: A Unified Framework For Spectral Dictionary Vllms2025Investigating Redundancy In Multimodal Large Language Models With Multiple Vision Encoders2025Optmerge: Unifying Multimodal LLM Capabilities And Modalities Via Model Merging2025PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs2025Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding2025VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization2025FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering2025Elevating Visual Question Answering through Implicitly Learned Reasoning Pathways in LVLMs2025Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection2025Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering2025Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension In Biomedical Image Analysis2025UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding2023 · 1 citesMMBench: Is Your Multi-modal Model an All-around Player?2023 · 33 citesHow to Configure Good In-Context Sequence for Visual Question Answering2023 · 3 citesMitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning2024 · 2 citesLXMERT Model Compression for Visual Question Answering2023 · 1 citesGenerative Visual Question Answering2023Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models2023Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs2023Improving Vision-and-Language Reasoning via Spatial Relations Modeling2023VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models2024Multi-Modal Hallucination Control by Visual Information Grounding2024Selectively Answering Visual Questions2024Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale2024Optimizing Vision-Language Interactions Through Decoder-Only Models2024Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes2024