9 articles tagged with #foundation-model. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers have developed the first 3D Lifting Foundation Model (3D-LFM) that can reconstruct 3D structures from 2D landmarks without requiring correspondence across training data. The model uses transformer architecture to achieve state-of-the-art performance across various object categories with resilience to occlusions and noise.
Stanford researchers introduced Merlin, a 3D vision-language foundation model for analyzing abdominal CT scans that processes volumetric medical images alongside electronic health records and radiology reports. The model was trained on over 6 million images from 15,331 CT scans and demonstrated superior performance compared to existing 2D models across 752 individual medical tasks.
Google has launched a new 27 billion parameter foundation model for single-cell analysis, built on the Gemma family of open models. The model has reportedly helped discover a new potential cancer therapy pathway, demonstrating practical medical applications of AI technology.
NVIDIA has made Evo 2, the largest publicly available AI foundation model for genomic data, accessible through its BioNeMo platform. The model was developed in collaboration with Arc Institute and can understand genetic code across all domains of life, built on NVIDIA's DGX Cloud platform.
Genie 2 is introduced as a large-scale foundation world model designed to generate unlimited diverse training environments. This development aims to support the creation and training of future general AI agents by providing varied simulation scenarios.
Researchers have developed HighFM, a foundation model for analyzing high-frequency Earth observation data using over 2TB of satellite imagery to enable real-time disaster monitoring. The model adapts masked autoencoding frameworks with temporal encodings to capture short-term environmental changes and demonstrates superior performance in cloud masking and fire detection tasks.
Researchers documented their experience training Summer-22B, a video foundation model developed from scratch using 50 million clips. The report details engineering challenges, dataset curation methods, and architectural decisions, emphasizing that dataset engineering consumed the majority of development effort.
Researchers introduce MultiPUFFIN, a multimodal AI foundation model that predicts molecular properties for drug discovery and materials science. The model combines multiple data types and thermodynamic principles to achieve superior performance while using 2000x fewer training molecules than existing models like ChemBERTa-2.
Researchers introduce FM-RME, a foundation model for radio map estimation that combines geometry-aware feature extraction with attention-based neural networks. The model uses self-supervised pre-training to enable zero-shot generalization across spatial, temporal, and spectral domains without scenario-specific retraining.
