The paper introduces LeWorldModel (LeWM), a stable Joint-Embedding Predictive Architecture (JEPA) that trains end-to-end directly from raw pixels. Unlike existing methods that rely on complex losses, pre-trained encoders, or auxiliary supervision to prevent representation collapse, LeWM uses only two loss terms: next-embedding prediction and Gaussian latent regularization. This approach significantly simplifies the training process by reducing tunable hyperparameters. The model is highly efficient, with approximately 15 million parameters capable of being trained on a single GPU within hours, and it offers planning speeds up to 48x faster than foundation-model-based world models while remaining competitive in 2D and 3D control tasks. Additionally, the latent space effectively encodes physical structures, allowing the model to detect physically implausible events through surprise evaluation.
Researchers from Columbia and Harvard have successfully used AI tools to engineer a portion of the E. coli ribosome that functions without isoleucine, one of the 20 standard amino acids. By replacing isoleucine with similar amino acids such as valine through iterative testing and deep-learning software, the team created an isoleucine-free small subunit in the bacteria. Although these engineered cells survived, they experienced slower growth rates than unmodified strains. This research investigates the possibility of simplified genetic codes and offers clues about how early life may have operated with fewer amino acids.
This article explores the critical intersection of knowledge graphs and data lineage in the context of modern AI and machine learning. It examines how combining these two technologies can provide the transparency and traceability required to build trustworthy AI systems. By mapping the origins, transformations, and movements of data, organizations can ensure better data quality, regulatory compliance, and improved model interpretability.
This research introduces a novel robot operating system (ROS) framework designed to seamlessly integrate large language models (LLMs) into embodied artificial intelligence. The framework enables robots to interpret and execute natural language instructions with greater versatility and reliability.
Key features include automatic translation of LLM outputs into robot actions, support for both code-based and behavior tree execution modes, and the ability to learn new skills through imitation and automated optimization.
Extensive experiments demonstrate the robustness and scalability of the framework across diverse scenarios, including complex tasks like coffee making and remote control. The complete implementation is available as open-source code, utilizing open-source pretrained LLMs.
Key features include automatic translation of LLM outputs into robot actions, support for both code-based and behavior tree execution modes, and the ability to learn new skills through imitation and automated optimization.
Extensive experiments demonstrate the robustness and scalability of the framework across diverse scenarios, including complex tasks like coffee making and remote control. The complete implementation is available as open-source code, utilizing open-source pretrained LLMs.
This is an open, unconventional textbook covering mathematics, computing, and artificial intelligence from foundational principles. It's designed for practitioners seeking a deep understanding, moving beyond exam preparation and focusing on real-world application. The author, drawing from years of experience in AI/ML, has compiled notes that prioritize intuition, context, and clear explanations, avoiding dense notation and outdated material.
The compendium covers a broad range of topics, from vectors and matrices to machine learning, computer vision, and multimodal learning, with future chapters planned for areas like data structures and AI inference.
The compendium covers a broad range of topics, from vectors and matrices to machine learning, computer vision, and multimodal learning, with future chapters planned for areas like data structures and AI inference.
This article details the rediscovery of the source code for AM and EURISKO, two groundbreaking AI programs created by Douglas Lenat in the 1970s and early 80s. AM autonomously rediscovered mathematical concepts, while EURISKO excelled in VLSI design and even defeated human players in the Traveller RPG. Lenat had previously stated he no longer possessed the code, but it was found archived on SAILDART, the original Stanford AI Laboratory backup data, and in printouts at the Computer History Museum. The code was password protected until Lenat's passing, and has now been made available on Github.
This essay argues that the economics of context engineering expose a gap in the Brynjolfsson-Hitzig framework that changes its practical implications: for how enterprises build with AI, which firms centralize successfully, and whether the AI economy will be as centralized as their framework suggests. It explores how the cost and effort required to make knowledge usable by AI—context engineering—creates a bottleneck that prevents complete centralization, preserving the importance of local knowledge and human judgment. The article discusses the implications for SaaS companies, knowledge workers, and the future of work in an AI-driven economy, predicting that those who invest in context engineering capabilities will see the highest ROI.
NVIDIA GTC is the premier AI conference and exhibition. Learn about the latest advancements in AI, deep learning, and accelerated computing. Includes keynote speakers, sessions, workshops, and an exhibit hall.
We’ve been experimenting with using large language models (LLMs) to assist in hardware design, and we’re excited to share our first project: the Deep Think PCB. This board is designed to be a versatile platform for experimenting with LLMs at the edge, and it’s built using a combination of open-source hardware and software. We detail the process of using Gemini to generate the schematic and PCB layout, the challenges we faced, and the lessons we learned. It's a fascinating look at the future of hardware design!
Sipeed’s MaixCAM2 is a powerful, open-source AI camera designed for makers, offering significant performance improvements over Raspberry Pi and OpenMV solutions. It features the Axera Tech AX630 AI SoC with up to 12.8 TOPS and supports training-free vision models and vision-language models.
