Foundation Models

ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation CVPR 2025 Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding CVPR 2025 Video-Bench: Human-Aligned Video Generation Benchmark CVPR 2025 VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM CVPR 2025 Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning EMNLP 2025 VideoWorld: Exploring Knowledge Learning from Unlabeled Videos CVPR 2025 VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge CVPR 2025 VIoTGPT: Learning to Schedule Vision Tools Towards Intelligent Video Internet of Things AAAI 2025 ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction AAAI 2025 Virtual CRISPR: Can LLMs Predict CRISPR Screen Results? ACL 2025 Vision-Language Models Can't See the Obvious ICCV 2025 VisionMath: Vision-Form Mathematical Problem-Solving ICCV 2025 VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters ICML 2025 VisNumBench: Evaluating Number Sense of Multimodal Large Language Models ICCV 2025 VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imaging CVPR 2025 VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents ICLR 2025 VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models COLING 2025 ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy ICML 2025 ViUniT: Visual Unit Tests for More Robust Visual Programming CVPR 2025 VIVA+: Human-Centered Situational Decision-Making EMNLP 2025 VLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training EMNLP 2025 VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning CVPR 2025 VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation EMNLP 2025 VPO: Aligning Text-to-Video Generation Models with Prompt Optimization ICCV 2025 VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding AAAI 2025