GQA

GQA is a benchmark that contains a diverse set of visual question answering tasks used to evaluate the performance of models in understanding and reasoning about images in conjunction with natural language.

Papers using GQA (23)

Hierarchical Pre-Training of Vision Encoders with Large Language Models2026AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning2026Hidden Clones: Exposing and Fixing Family Bias in Vision-Language Model Ensembles2026VOILA: Value-of-Information Guided Fidelity Selection for Cost-Aware Multimodal Question Answering2026How Vision Becomes Language: A Layer-wise Information-Theoretic Analysis of Multimodal Reasoning2026Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs2026HybridToken-VLM: Hybrid Token Compression for Vision-Language Models2025Efficient Vision-Language Reasoning via Adaptive Token Pruning2025MV-CoRe: Multimodal Visual-Conceptual Reasoning for Complex Visual Question Answering2025MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models2025Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding2025ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way2025ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM2025Constructive Distortion: Improving Mllms With Attention-guided Image Warping2025Test-time Warmup For Multimodal Large Language Models2025Multi-Sourced Compositional Generalization in Visual Question Answering2025II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question Answering2024 · 1 citesTowards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models2023LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering2024Efficient Large Multi-modal Models via Visual Context Compression2024SADL: An Effective In-Context Learning Method for Compositional Visual QA2024Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy2024Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes2024