Vision-Language Models

CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models AAAI 2025 Concept-pedia: a Wide-coverage Semantically-annotated Multimodal Dataset EMNLP 2025 Conical Visual Concentration for Efficient Large Vision-Language Models CVPR 2025 CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG ACL 2025 COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training CVPR 2025 Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning CVPR 2025 Cross-Modal 3D Representation with Multi-View Images and Point Clouds CVPR 2025 Data or Language Supervision: What Makes CLIP Better than DINO? EMNLP 2025 Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics ACL 2025 Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices EMNLP 2025 DepthCues: Evaluating Monocular Depth Perception in Large Vision Models CVPR 2025 Design Choices for Extending the Context Length of Visual Language Models ACL 2025 Detecting and Mitigating Challenges in Zero-Shot Video Summarization with Video LLMs ACL 2025 Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback AAAI 2025 Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding EMNLP 2025 DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models WACV 2025 DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models CVPR 2025 DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models’ Understanding on Indian Culture EMNLP 2025 Dual Semantic Guidance for Open Vocabulary Semantic Segmentation CVPR 2025 DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models CVPR 2025 EAGLE: Expert-Guided Self-Enhancement for Preference Alignment in Pathology Large Vision-Language Model ACL 2025 ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark CVPR 2025 EcoDoc: A Cost-Efficient Multimodal Document Processing System for Enterprises Using LLMs ACL 2025 Enhance Vision-Language Alignment with Noise AAAI 2025 Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality Calibration CVPR 2025