{"id":1869,"date":"2025-11-16T10:19:56","date_gmt":"2025-11-16T10:19:56","guid":{"rendered":"https:\/\/scipapermill.com\/index.php\/2025\/11\/16\/foundation-models-unleashed-from-drug-discovery-to-urban-intelligence-ais-new-horizons\/"},"modified":"2025-12-28T21:22:17","modified_gmt":"2025-12-28T21:22:17","slug":"foundation-models-unleashed-from-drug-discovery-to-urban-intelligence-ais-new-horizons","status":"publish","type":"post","link":"https:\/\/scipapermill.com\/index.php\/2025\/11\/16\/foundation-models-unleashed-from-drug-discovery-to-urban-intelligence-ais-new-horizons\/","title":{"rendered":"Foundation Models Unleashed: From Drug Discovery to Urban Intelligence, AI’s New Horizons"},"content":{"rendered":"

Latest 50 papers on foundation models: Nov. 16, 2025<\/h3>\n

The world of AI\/ML is buzzing with the transformative power of foundation models, monumental architectures pre-trained on vast datasets that offer unparalleled generalization capabilities. These models are not just about scale; they represent a paradigm shift, enabling rapid adaptation to new tasks and domains with remarkable efficiency. Yet, harnessing their full potential often involves navigating complex challenges, from data scarcity and privacy concerns to maintaining robustness and interpretability. Recent breakthroughs, as highlighted by a collection of cutting-edge research, are pushing the boundaries of what\u2019s possible, extending the reach of foundation models into diverse, high-impact applications.<\/p>\n

The Big Idea(s) & Core Innovations:<\/h3>\n

This wave of innovation spans multiple domains, unified by the strategic application and enhancement of foundation models. In drug discovery<\/strong>, Terray Therapeutics researchers, in their paper \u201cPretrained Joint Predictions for Scalable Batch Bayesian Optimization of Molecular Designs<\/a>\u201d, are accelerating the process by integrating pretrained prior functions into Epistemic Neural Networks (ENNs). This significantly boosts the efficiency and accuracy of Batch Bayesian Optimization for molecular design, enabling rapid sampling from joint predictive distributions\u2014a critical step in optimizing large-scale drug discovery. Similarly, the biomedical field is seeing a surge in advanced models. \u201cvMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs<\/a>\u201d by authors from Durham University and Tsinghua University, introduces vMFCoOp, a framework that aligns semantic biases in Vision-Language Models (VLMs) and LLMs on a hyperspherical manifold, enhancing few-shot learning and clinical applicability across diverse medical modalities. Another significant leap in medical imaging<\/strong> comes from the Technical University of Munich and King\u2019s College London with \u201cTomoGraphView: 3D Medical Image Classification with Omnidirectional Slice Representations and Graph Neural Networks<\/a>\u201d. TomoGraphView introduces omnidirectional volume slicing and spherical graph-based feature aggregation, outperforming traditional methods in 3D medical image classification by better capturing spatial relationships.<\/p>\n

Computer vision<\/strong> is experiencing multifaceted advancements. The \u201cOmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer<\/a>\u201d by researchers from HKUST, NTU, and Alibaba Group, leverages multiple geometric modalities (depth, camera intrinsics\/extrinsics) for superior 3D reconstruction and robotic manipulation. Their GeoAdapter injects geometric information without disrupting the foundation model\u2019s representation space, ensuring stable training. In e-commerce<\/strong>, the Ohio State University team, in their work \u201cCaptions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data<\/a>\u201d, introduced MMECInstruct and CASLIE, a lightweight framework for multimodal understanding, demonstrating the power of high-quality multimodal data for better product insights. Addressing crucial ethical concerns, \u201cPrivacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding<\/a>\u201d by the University of Central Florida proposes SPLAVU, a novel method for anonymizing latent features in video, significantly reducing privacy leakage while maintaining task performance. For time series analysis<\/strong>, papers like \u201cSpectral Predictability as a Fast Reliability Indicator for Time Series Forecasting Model Selection<\/a>\u201d from UCLA introduce spectral predictability (\u2119) as a crucial metric for efficient model selection, revealing that large Time Series Foundation Models (TSFMs) excel in high-predictability datasets. Building on this, \u201cAre Time-Indexed Foundation Models the Future of Time Series Imputation?<\/a>\u201d by EDF R&D demonstrates the robust zero-shot imputation capabilities of models like TabPFN-TS and MoTM across diverse datasets.<\/p>\n

Under the Hood: Models, Datasets, & Benchmarks:<\/h3>\n

These innovations are powered by new models, enhanced architectures, and meticulously crafted datasets and benchmarks:<\/p>\n