Foundation Models

Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D EMNLP 2025 Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts ICCV 2025 Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild ICCV 2025 CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology CVPR 2025 Detect Anything 3D in the Wild ICCV 2025 DexVLG: Dexterous Vision-Language-Grasp Model at Scale ICCV 2025 DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation ICCV 2025 Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models ICLR 2025 EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions CVPR 2025 Empirical Analysis of Scaling Vision Foundation Models for Chest X-rays MIDL 2025 Enhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings EMNLP 2025 Enhancing Novel Object Detection via Cooperative Foundational Models WACV 2025 Enhancing Prompt Generation with Adaptive Refinement for Camouflaged Object Detection ICCV 2025 Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection ICCV 2025 F^3OCUS - Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics CVPR 2025 F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration ICCV 2025 Feat2GS: Probing Visual Foundation Models with Gaussian Splatting CVPR 2025 FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation ICCV 2025 Federated Foundation Models on Heterogeneous Time Series AAAI 2025 Find Any Part in 3D ICCV 2025 Fine-Tuning with Uncertainty-Aware Priors Makes Vision and Language Foundation Models More Reliable AISTATS 2025 FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation ACL 2025 FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records IJCAI 2025 Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion CVPR 2025 fLSA: Learning Semantic Structures in Document Collections Using Foundation Models EMNLP 2025