Visual Question Answering

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation CVPR 2026 Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow CVPR 2026 A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning CVPR 2026 AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models CVPR 2026 CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering CVPR 2026 ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch ACL 2026 Decoupling Vision and Reasoning: A Data-Efficient Pipeline for Surgical VQA MIDL 2026 DIAGRAMS : A Review Framework for Reasoning-Level Attribution in Diagram QA ACL 2026 DiGraphHal-Bench: Evaluating Multimodal Large Language Models on Complex Directed Graphs CVPR 2026 Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering CVPR 2026 Dual-Level Confidence based Implicit Self-Refinement for Medical Visual Question Answering CVPR 2026 EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy CVPR 2026 Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering ACL 2026 HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models CVPR 2026 Hear you are: Teaching LLMs Spatial Reasoning with Vision and Spatial Sound CVPR 2026 HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering CVPR 2026 HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models CVPR 2026 M3Grounder: Mask-Based Multi-Span and Multi-Granular Grounding for Document QA CVPR 2026 MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems ACL 2026 MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA CVPR 2026 Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding CVPR 2026 More than the Sum: Panorama-Language Models for Adverse Omni-Scenes CVPR 2026 MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark CVPR 2026 MR-RAG: Multimodal Relevance-Aware Retrieval-Augmented Generation for Medical Visual Question Answering CVPR 2026 OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks CVPR 2026