Foundation Models

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens CVPR 2026 AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models CVPR 2026 Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning CVPR 2026 MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts CVPR 2026 SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models CVPR 2026 Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning CVPR 2026 The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification CVPR 2026 UniPercept: A Unified Diffusion Model for Generalizable Visual Perception CVPR 2026 UniVBench: Towards Unified Evaluation for Video Foundation Models CVPR 2026 V^2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence CVPR 2026 VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment CVPR 2026 Agtech Framework for Cranberry-Ripening Analysis using Vision Foundation Models WACV 2025 Argus: A Compact and Versatile Foundation Model for Vision CVPR 2025 COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation CVPR 2025 Exploring Task-Level Optimal Prompts for Visual In-Context Learning AAAI 2025 FoundationStereo: Zero-Shot Stereo Matching CVPR 2025 Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration CVPR 2025 Interpreting Object-level Foundation Models via Visual Precision Search CVPR 2025 LaVin-DiT: Large Vision Diffusion Transformer CVPR 2025 Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models ICCV 2025 Shadow Removal Refinement via Material-Consistent Shadow Edges WACV 2025 Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model CVPR 2025 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities NeurIPS 2024 Aligning and Prompting Everything All at Once for Universal Visual Perception CVPR 2024 AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning CVPR 2024