Multimodal Learning

Vision-Language Models Can't See the Obvious ICCV 2025 Vision-Language Models Create Cross-Modal Task Representations ICML 2025 Vision-Language Models Do Not Understand Negation CVPR 2025 Vision-Language Model Selection and Reuse for Downstream Adaptation ICML 2025 Vision-Language Models Struggle to Align Entities across Modalities ACL 2025 Vision-Language Neural Graph Featurization for Extracting Retinal Lesions ICCV 2025 VisionMath: Vision-Form Mathematical Problem-Solving ICCV 2025 VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters ICML 2025 VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs EMNLP 2025 VisNumBench: Evaluating Number Sense of Multimodal Large Language Models ICCV 2025 VISO: Accelerating In-orbit Object Detection with Language-Guided Mask Learning and Sparse Inference ICCV 2025 ViSpeak: Visual Instruction Feedback in Streaming Videos ICCV 2025 VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents ICLR 2025 VisRL: Intention-Driven Visual Perception via Reinforced Reasoning ICCV 2025 VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation CVPR 2025 VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft EMNLP 2025 VisTRA: Visual Tool-use Reasoning Analyzer for Small Object Visual Question Answering ACL 2025 Visual Abstraction: A Plug-and-Play Approach for Text-Visual Retrieval ICML 2025 VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents ICLR 2025 Visual Agents as Fast and Slow Thinkers ICLR 2025 Visual and Domain Knowledge for Professional-level Graph-of-Thought Medical Reasoning ICML 2025 Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning CVPR 2025 Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models ICML 2025 Visual-Aware Speech Recognition for Noisy Scenarios EMNLP 2025 Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images ICCV 2025