Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
GGUF, GPTQ, and AWQ are the three dominant formats for running quantized large language models locally, each optimized for different hardware and use cases. GGUF, the format used by llama.cpp and its derivatives, offers …
The Global AI Oversight Board (GAIOB) issued a €500 million fine against CognitoSync Labs for algorithmic bias in a financial lending platform and lack of explainability under the new Global AI Act of 2025. The penalty m…
A former Meta engineer has launched a five-part series called "Unpacking AI" to explain artificial intelligence from the ground up, starting with the hardware that powers it. The first installment covers transistors, sem…
A Hacker News user questioned whether computer science professors were correct to de-emphasize programming in their courses, given that modern AI can now automate routine coding tasks. The post suggests that what was onc…
Researchers have established a mathematical correspondence between hierarchical decision trees and diffusion processes, unifying the two model classes under a shared optimization principle called Global Trajectory Score …
More than 100 engineers cloned a free open-source handbook on large language model inference within its first week of release. The guide consolidates years of production experience and research to address the unique chal…
OpenCV 5.0 was released today as a major update to the open-source computer vision library, featuring a rewritten deep neural network engine and built-in support for large language and vision language models. The new ver…
Mbodi AI, a Y Combinator-backed startup building an embodied AI platform that enables industrial robots to learn and operate like humans through natural language, is hiring a founding machine learning engineer focused on…
Researchers Sebastian Raschka released a curated list of LLM research papers from January to May 2026, focusing on reasoning models, reinforcement learning, and efficient inference. The list, organized into categories li…
The New Stack reports that transitioning AI systems from Jupyter Notebook experimentation to production demands fundamental shifts in mindset, architecture, and engineering discipline, with no reliance on API wrappers. T…
A new open-source voice model, Audio Interaction, processes audio continuously, deciding every 0.4 seconds whether to speak or remain silent, unlike models that wait for recordings to end. It translates, transcribes, and…
Machine learning, deep learning, and reinforcement learning are three distinct approaches that enable computers to learn tasks without explicit instructions. Machine learning uses algorithms like linear regression and de…
ESA researchers David O'Ryan and Pablo Gómez used an AI tool called AnomalyMatch to scan nearly 100 million image cutouts from the Hubble Legacy Archive, identifying roughly 1,400 anomalous objects in about two and a hal…
A developer has built a carbon-aware training pipeline for PyTorch that schedules GPU workloads around real-time electricity carbon intensity, reducing CO2 emissions by delaying training until low-carbon windows are avai…
A developer has built a Financial Risk Intelligence Agent that learns from past investigations rather than evaluating each transaction independently. The system uses a memory-powered architecture that stores investigatio…
The University of Cambridge and biotech firm DIOSynVax Ltd announced on June 5 that a Phase I clinical trial of 39 healthy volunteers showed their AI-designed vaccine is safe, well-tolerated, and triggered immune respons…
In a single week, open-weight AI models expanded across nearly every major modality, including frontier-scale LLMs, multimodal laptop models, image generators, multilingual TTS, real-time music models, streaming ASR, doc…
A developer at Gemini implemented a Model Registry with an extended schema and automated logging to track cost metadata per AI task and tier, solving a critical inefficiency in model versioning and expense management. Th…
NVIDIA released Nemotron 3.5 ASR, a 600M-parameter streaming speech recognition model that transcribes 40 language-locales in real time from a single checkpoint. The model uses a cache-aware FastConformer-RNNT architectu…
Access to a research paper titled "Adaptive Low-Rank Transformer with Dynamic Expert Routing for Continual Learning" has been blocked due to unusual traffic from the user's network. The restriction was triggered at 09:16…