Vision-Language Models

Leveraging Class Distributions in CLIP for Weakly Supervised Semantic Segmentation CVPR 2026 Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System ACL 2026 Lifting Unlabeled Internet-level Data for 3D Scene Understanding CVPR 2026 Limited Linguistic Diversity in Embodied AI Datasets ACL 2026 LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding CVPR 2026 LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models CVPR 2026 LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models CVPR 2026 Localizing, Structuring, and Rendering: Bridging 3D and 2D Vision-Language-Action Models for Robotic Manipulation CVPR 2026 LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight CVPR 2026 Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation CVPR 2026 LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation CVPR 2026 Looking Beyond the One: Operationalizing and Eliciting Visual Ambiguity in VLLMs ACL 2026 Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation CVPR 2026 Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning ACL 2026 LOREAL: Mitigating Low-Resolution Challenges in Vision-Language Models with Attribute-driven Prompt Self-Distillation CVPR 2026 LVLM-Aided Alignment of Task-Specific Vision Models CVPR 2026 LVLMs and Humans Ground Differently in Referential Communication ACL 2026 Lynx: Towards High-Fidelity Personalized Video Generation CVPR 2026 M3Grounder: Mask-Based Multi-Span and Multi-Granular Grounding for Document QA CVPR 2026 M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG CVPR 2026 Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens CVPR 2026 MagicBench: Diagnosing Visual Agency Loss and Semantic Dependency in Multimodal LLMs ACL 2026 Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight CVPR 2026 MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization CVPR 2026 Masking Teacher and Reinforcing Student for Distilling Vision-Language Models CVPR 2026