visual understanding

Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models CVPR 2026 MagicBench: Diagnosing Visual Agency Loss and Semantic Dependency in Multimodal LLMs ACL 2026 Mitigating Low-Quality Reasoning in MLLMs: Self-Driven Refined Multimodal CoT with Selective Thinking and Step-wise Visual Enhancement AAAI 2026 MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning CVPR 2026 RMIR: A Benchmark Dataset for Reasoning-Intensive Multimodal Image Retrieval CVPR 2026 SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination WACV 2026 Taming the Phantom: Token-Asymmetric Filtering for Hallucination Mitigation in Large Vision-Language Models AAAI 2026 Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark ACL 2026 VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes CVPR 2026 AlgoPuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Algorithmic Multimodal Puzzles NAACL 2025 An Investigation on LLMs' Visual Understanding Ability using SVG for Image-Text Bridging WACV 2025 Can Machines Understand Composition? Dataset and Benchmark for Photographic Image Composition Embedding and Understanding CVPR 2025 ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation ICLR 2025 Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment CVPR 2025 CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models CVPR 2025 Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering NAACL 2025 Don’t Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models ACL 2025 Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation EMNLP 2025 From Image to Video: An Empirical Study of Diffusion Representations ICCV 2025 From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning ICCV 2025 Harmonizing Visual Representations for Unified Multimodal Understanding and Generation ICCV 2025 Is `Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning CVPR 2025 MetaMorph: Multimodal Understanding and Generation via Instruction Tuning ICCV 2025 Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow EMNLP 2025 Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models ICCV 2025