Vision-Language Models

Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM CVPR 2026 Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofing CVPR 2026 How Do Inpainting Artifacts Propagate to Language? ACL 2026 Hybrid Token Compression for Vision-Language Models CVPR 2026 Incentivizing Versatile Video Reasoning in MLLMs via Data-Efficient Reinforcement Learning CVPR 2026 INFORM-CT: INtegrating LLMs and VLMs FOR Incidental Findings Management in Abdominal CT MIDL 2026 IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment CVPR 2026 JW-SVD: Bridging the Cross-Modal Mismatch in Post-Training MLLM Compression ACL 2026 Learning from Itself: Mining Internal Knowledge from Vision Language Models for Continual Learning CVPR 2026 Learning to Diversify and Focus: A Reinforcement Framework for Open-Vocabulary HOI Detection CVPR 2026 Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding CVPR 2026 Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images CVPR 2026 MA-Bench: Towards Fine-grained Micro-Action Understanding CVPR 2026 MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation ACL 2026 MARIS: Marine Open-Vocabulary Instance Segmentation CVPR 2026 MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation CVPR 2026 MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images CVPR 2026 Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning CVPR 2026 MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing ACL 2026 Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection CVPR 2026 MLLMSplat: A 2D MLLM-Powered Framework for 3D Gaussian Splatting Understanding, Generation, and Editing CVPR 2026 MM-ACT: Learn from Multimodal Parallel Generation to Act CVPR 2026 MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping CVPR 2026 MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection CVPR 2026 Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding CVPR 2026