Core AI

UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction ICCV 2025 Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation CVPR 2025 Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering EMNLP 2025 Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints ICCV 2025 UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios AAAI 2025 UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction WACV 2025 VADE: Visual Attention Guided Hallucination Detection and Elimination ACL 2025 VAQUUM: Are Vague Quantifiers Grounded in Visual Data? ACL 2025 VarCMP: Adapting Cross-Modal Pre-Training Models for Video Anomaly Retrieval AAAI 2025 VCD: A Dataset for Visual Commonsense Discovery in Images ACL 2025 VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image Captions EMNLP 2025 VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping AAAI 2025 VideoGameBunny: Towards Vision Assistants for Video Games WACV 2025 VideoGEM: Training-free Action Grounding in Videos CVPR 2025 VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos CVPR 2025 VideoRAG: Retrieval-Augmented Generation over Video Corpus ACL 2025 ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents EMNLP 2025 Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation Learning CVPR 2025 ViFT: Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models EMNLP 2025 ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding ACL 2025 ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention AAAI 2025 VIIS: Visible and Infrared Information Synthesis for Severe Low-Light Image Enhancement WACV 2025 ViLBench: A Suite for Vision-Language Process Reward Modeling EMNLP 2025 VILLS : Video-Image Learning to Learn Semantics for Person Re-Identification WACV 2025 ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba ICCV 2025