Foundation Models

MORE: Molecule Pretraining with Multi-Level Pretext Task AAAI 2025 Multifaceted User Modeling in Recommendation: A Federated Foundation Models Approach AAAI 2025 No Audiogram: Leveraging Existing Scores for Personalized Speech Intelligibility Prediction Interspeech 2025 Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models ICCV 2025 OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad CVPR 2025 OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning ICCV 2025 OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary Interspeech 2025 OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning Interspeech 2025 Parameter Efficient Fine-Tuning of Segment Anything Model for Biomedical Imaging MIDL 2025 Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation WACV 2025 Physics-Guided Foundation Model for Scientific Discovery: An Application to Aquatic Science AAAI 2025 Pos3R: 6D Pose Estimation for Unseen Objects Made Easy CVPR 2025 Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing CVPR 2025 Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners AISTATS 2025 RoboTron-Mani: All-in-One Multimodal Large Model for Robotic Manipulation ICCV 2025 SAM4D: Segment Anything in Camera and LiDAR Streams ICCV 2025 SapiensID: Foundation for Human Recognition CVPR 2025 SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection AAAI 2025 Scalable Vision Language Model Training via High Quality Data Curation ACL 2025 Scaling Laws for Native Multimodal Models ICCV 2025 Scaling Omni-modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities ICCV 2025 Scaling Supervision for Free: Leveraging Universal Segmentation Models for Enhanced Medical Image Diagnosis MIDL 2025 SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers EMNLP 2025 Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era ACL 2025 SegAnyPET: Universal Promptable Segmentation from Positron Emission Tomography Images ICCV 2025