foundation models

30 articles about foundation models in AI news

VAST's $50M Funding Signals 3D AI Revolution: From Foundation Models to World Simulation

AI startup VAST has secured $50 million in Series A funding while advancing its 3D foundation models that are setting new industry standards. The company is preparing to launch its first world model, positioning itself at the forefront of spatial AI development.

80% relevant

Beyond General AI: How Liquid Foundation Models Are Revolutionizing Drug Discovery

Researchers have developed MMAI Gym, a specialized training platform that teaches AI the 'language of molecules' to create more efficient drug discovery models. The resulting Liquid Foundation Models outperform larger general-purpose AI while requiring fewer computational resources.

85% relevant

Apple Siri Rebuilt as System-Wide AI Agent in iOS 27, Powered by Apple Foundation Models and Google Gemini

Apple is rebuilding Siri into a conversational system-wide AI agent with deep app integration and personal data access, launching in iOS 27. The overhaul includes a standalone app, web browsing, and writing tools, powered by Apple's models and a Google Gemini partnership.

95% relevant

Mercor Data Breach Exposes Expert Human Annotation Pipeline Used by Frontier AI Labs

Hackers have reportedly accessed Mercor's expert human data collection systems, which are used by leading AI labs to build foundation models. This breach could expose proprietary training methodologies and sensitive model development data.

91% relevant

Geometric Latent Diffusion (GLD) Achieves SOTA Novel View Synthesis, Trains 4.4× Faster Than VAE

GLD repurposes features from geometric foundation models like Depth Anything 3 as a latent space for multi-view diffusion. It trains significantly faster than VAE-based approaches and achieves state-of-the-art novel view synthesis without text-to-image pretraining.

95% relevant

CausalTimePrior: The Missing Link for AI That Understands Time and Cause

Researchers have introduced CausalTimePrior, a new framework to generate synthetic time series data with known interventions. This breakthrough addresses a critical gap in training AI models to understand causality over time, paving the way for foundation models in time series analysis.

100% relevant

NeuroSkill: MIT's Breakthrough AI Agent Reads Your Mind Before You Ask

MIT researchers have developed NeuroSkill, a revolutionary AI system that integrates brain-computer interfaces with foundation models to create proactive agents that respond to implicit human cognitive and emotional states, running fully offline on edge devices.

85% relevant

Time-Series AI Learns to Adapt on the Fly: New Framework Eliminates Fine-Tuning for Unseen Tasks

Researchers have developed ICTP, a framework that equips time-series foundation models with in-context learning capabilities, allowing them to adapt to completely new tasks without fine-tuning. This breakthrough improves performance on unseen tasks by 11.4% and represents a significant step toward more flexible, efficient AI systems for real-world time-series applications.

78% relevant

Bridging Data Worlds: How MultiModalPFN Unifies Tabular, Image, and Text Analysis

Researchers have developed MultiModalPFN, an AI framework that extends TabPFN to handle tabular data alongside images and text. This breakthrough addresses a critical limitation in foundation models for structured data, enabling more comprehensive analysis in healthcare, marketing, and other domains where multiple data types coexist.

72% relevant

Hitachi's Industrial Gambit: Why Domain Expertise May Be the Missing Link in Physical AI

While tech giants focus on foundation models, Hitachi is betting its industrial expertise and operational data will win the physical AI race. The company's partnerships with Daikin and JR East demonstrate how domain knowledge bridges the gap between digital intelligence and real-world machinery.

75% relevant

CanViT: First Active-Vision Foundation Model Hits 45.9% mIoU on ADE20K with Sequential Glimpses

Researchers introduce CanViT, the first task- and policy-agnostic Active-Vision Foundation Model (AVFM). It achieves 38.5% mIoU on ADE20K segmentation with a single low-resolution glimpse, outperforming prior active models while using 19.5x fewer FLOPs.

91% relevant

VMLOPS's 'Basics' Repository Hits 98k Stars as AI Engineers Seek Foundational Systems Knowledge

A viral GitHub repository aggregating foundational resources for distributed systems, latency, and security has reached 98,000 stars. It addresses a widespread gap in formal AI and ML engineering education, where critical production skills are often learned reactively during outages.

75% relevant

Google Open-Sources TimesFM: A 100B-Point Time Series Foundation Model for Zero-Shot Forecasting

Google has open-sourced TimesFM, a foundation model for time series forecasting trained on 100 billion real-world time points. It requires no dataset-specific training and can generate predictions instantly for domains like traffic, weather, and demand.

95% relevant

Seed1.8 Model Card Released: A 1.8B Parameter Foundation Model for Generalized Real-World AI Agents

Researchers have introduced Seed1.8, a 1.8 billion parameter foundation model designed for generalized real-world agency. It maintains strong LLM and vision-language capabilities while adding unified interfaces for search, code execution, and GUI interaction.

99% relevant

Anthropic Donates to Linux Foundation, Citing Critical Need for Open Source AI Security

Anthropic announced a donation to the Linux Foundation to support securing open source software, which it calls the foundation AI runs on. The move highlights growing industry focus on securing the software supply chain for AI systems.

85% relevant

Google's TimesFM Foundation Model: A New Paradigm for Time Series Forecasting

Google Research has open-sourced TimesFM, a 200 million parameter foundation model for time series forecasting. Trained on 100 billion real-world time points, it demonstrates remarkable zero-shot forecasting capabilities across diverse domains without task-specific training.

85% relevant

The Fragile Foundation: How AI Lab Failures Could Trigger a $1.5 Trillion Infrastructure Collapse

A Reuters analysis reveals that the failure of major AI labs like OpenAI or Anthropic could trigger a catastrophic chain reaction, jeopardizing the $650 billion data center boom and $900 billion in financial investments that depend on their insatiable demand for computing power.

85% relevant

Google Launches Gemini Embedding 2: A New Multimodal Foundation for AI

Google has launched Gemini Embedding 2, a second-generation multimodal embedding model. This technical release, alongside the removal of API rate limits, provides developers with a more powerful and accessible tool for building AI applications that understand text, images, and other data types.

99% relevant

Google Launches Gemini Embedding 2: A New Multimodal Foundation for AI Applications

Google has released Gemini Embedding 2, a second-generation multimodal embedding model designed to process text, images, and audio simultaneously. This technical advancement creates more unified AI representations, potentially improving search, recommendation, and personalization systems.

77% relevant

The AI Inflection Point: How Small Teams Are Reshaping Our Foundational Systems

As organizations redesign core systems for AI integration, a unique window of opportunity has emerged for small groups to establish patterns that could define how these systems operate for decades to come.

85% relevant

Sam Altman Predicts Next 'Transformer-Level' Architecture Breakthrough, Says AI Models Are Now Smart Enough to Help Find It

OpenAI CEO Sam Altman stated he believes a new AI architecture, offering gains as significant as transformers over LSTMs, is yet to be discovered. He argues current advanced models are now sufficiently capable of assisting in that foundational research.

87% relevant

rs-embed: The Universal Translator for Remote Sensing AI Models

Researchers have developed rs-embed, a Python library that provides unified access to remote sensing foundation model embeddings. This breakthrough addresses fragmentation in the field by allowing users to retrieve embeddings from any supported model for any location and time with a single line of code.

75% relevant

Why Deduplication Is the Most Underestimated Step in LLM Pretraining

A technical article on Medium argues that data deduplication is a critical, often overlooked step in LLM pretraining, directly impacting model performance and training cost. This is a foundational engineering concern for any team building or fine-tuning custom models.

86% relevant

A Comparative Guide to LLM Customization Strategies: Prompt Engineering, RAG, and Fine-Tuning

An overview of the three primary methods for customizing Large Language Models—Prompt Engineering, Retrieval-Augmented Generation (RAG), and Fine-Tuning—detailing their respective strengths, costs, and ideal use cases. This framework is essential for AI teams deciding how to tailor foundational models to specific business needs.

80% relevant

Luma Labs Launches Uni-1: An Autoregressive Transformer for Image Generation with a Pre-Generation Reasoning Phase

Luma Labs has released Uni-1, a foundational image model that uses an autoregressive transformer to reason about user intent before generating pixels. It aims to address the 'intent gap' common in diffusion models by adding a structured reasoning step.

88% relevant

8 AI Model Architectures Visually Explained: From Transformers to CNNs and VAEs

A visual guide maps eight foundational AI model architectures, including Transformers, CNNs, and VAEs, providing a clear reference for understanding specialized models beyond LLMs.

85% relevant

Jensen Huang's '5-Layer Cake': Nvidia CEO Redefines AI as Industrial Infrastructure

Nvidia CEO Jensen Huang introduces a revolutionary framework positioning AI as essential infrastructure spanning energy, chips, infrastructure, models, and applications. This industrial perspective reshapes how we understand AI's technological and economic foundations.

85% relevant

Google's TimesFM: The Zero-Shot Time Series Model That Works Without Training

Google has open-sourced TimesFM, a foundation model for time series forecasting that requires no training on specific datasets. Unlike traditional models, it can make predictions directly from historical data, potentially revolutionizing forecasting across industries.

95% relevant

Chamath Palihapitiya: AI's Biggest Profits Won't Go to Model Makers

VC Chamath Palihapitiya posits that the greatest financial winners in AI will be application builders with unique distribution, not the foundational model creators, drawing a parallel to refrigeration and Coca-Cola.

75% relevant

How Personalized Recommendation Engines Drive Engagement in OTT Platforms

A technical blog post on Medium emphasizes the critical role of personalized recommendation engines in Over-The-Top (OTT) media platforms, citing that most viewer engagement is driven by algorithmic suggestions rather than active search. This reinforces the foundational importance of recommendation systems in digital content consumption.

81% relevant