Vision-Language Models

SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models CVPR 2026 Sparse Spectral LoRA: Routed Experts for Medical VLMs CVPR 2026 Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos CVPR 2026 SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation CVPR 2026 Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery CVPR 2026 STAR: Test-Time Adaptation Can Enhance Universal Prompt Learning for Vision-Language Models CVPR 2026 Streaming Video Instruction Tuning CVPR 2026 Structural Graph Probing of Vision-Language Models CVPR 2026 Synthetic Vasculature and Pathology Enhance Vision-Language Model Reasoning MIDL 2026 TextFM: Robust Semi-dense Feature Matching with Language Guidance CVPR 2026 The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models ACL 2026 The olmOCR Project: Building Fully Open OCR using VLMs ACL 2026 Towards Calibrating Prompt Tuning of Vision- Language Models CVPR 2026 Towards Unified Human Perception and Machine Understanding: Token Flow Guided Compression Framework CVPR 2026 Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models CVPR 2026 UniCompress: Token Compression for Unified Vision-Language Understanding and Generation CVPR 2026 Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimization CVPR 2026 Unifying Language-Action Understanding and Generation for Autonomous Driving CVPR 2026 Universal 3D Shape Matching via Coarse-to-Fine Language Guidance CVPR 2026 Unleashing Vision-Language Semantics for Deepfake Video Detection CVPR 2026 V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs CVPR 2026 VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging CVPR 2026 Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure CVPR 2026 VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck ACL 2026 VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA CVPR 2026