Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Microsoft has open-sourced its ML Video Codec (MLVC), a machine learning-based video compression technology designed to improve efficiency and quality. The release on GitHub includes the codec's source code, models, and …
Principles of Intelligence (PrincInt, formerly PIBBSS) is launching PIRAMID, an internal research division that uses statistical physics to build scientific foundations for ambitious mechanistic interpretability. The div…
Google Research released TabFM on July 1, a foundation model for tabular data that achieves zero-shot classification and regression with no training or hyperparameter tuning, beating Optuna-tuned XGBoost on all 10 fold-m…
Primate Labs released Geekbench 7, a major overhaul of the cross-platform benchmark suite with updated CPU and GPU tests, including NVIDIA CUDA support. The CPU benchmark now includes a media group and uses a Lenovo Legi…
A model that achieves 90% accuracy on an imbalanced dataset can be completely useless, as it may simply predict the majority class every time, according to a technical analysis of confusion matrices. The author argues th…
OpenSquilla's SquillaRouter uses a small on-device machine learning model to route each agent turn to the cheapest capable LLM provider, treating model choice as a live routing problem rather than a static config. The mi…
A developer explored the VModal Flutter SDK, a modular client library for AI-powered video search. The SDK provides a clean architecture with resource-based organization, signed URL uploads, and semantic search capabilit…
Embeddings map words and concepts into a multi-dimensional vector space where similar meanings cluster together, enabling semantic search and Retrieval-Augmented Generation (RAG) systems to retrieve relevant information …
Letta AI introduced the Trajectory package, a standardized data format for agent experience that reduces token counts by up to 5.6× compared to native session formats, enabling agents to learn across harnesses such as Cl…
A developer compiled the top 10 most upvoted papers on Hugging Face, covering deep research agents, post-training large models on Ascend SuperPOD, embodied visual tracking, K-12 knowledge graphs, self-distillation for vi…
A developer implemented a usage-reinforced decay engine based on the Ebbinghaus forgetting curve to prevent context loss in AI agents. The system assigns a strength score to each memory, applying exponential decay that s…
To choose the right AI model from Hugging Face, users should first define their use case, such as chatbot, text classification, summarization, translation, or image generation, then use model filters to narrow options an…
A developer built a tiny language model in pure Node.js with no dependencies, implementing tokenization, embeddings, causal Transformer blocks, and backpropagation from scratch. The model trains on simple sentence patter…
Researchers introduced TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with past and future covariates, achieving state-of-the-art zero-shot…
A developer published a guide covering the essential mathematical concepts that power modern AI and large language models, explaining how text is tokenized, embedded, and processed through a transformer pipeline to predi…
A developer is revisiting linear algebra, statistics, and calculus textbooks to understand the math behind custom LLM layers and paper architectures, aiming to move from being a library user to someone who can optimize d…
Creativity is a core ML engineering skill because it enables engineers to ask the right questions and notice overlooked connections, which is critical as AI automates tool-use tasks, according to a professional AI workfl…
A developer building a self-hosted PHP media server achieved 99.83% title extraction cleanliness from 39,188 torrent filenames by truncating at the first technical marker instead of enumerating known tags. The approach, …
A developer building a personalized read-aloud picture book found that zero-shot TTS achieves usable speaker similarity from clips measured in seconds, but sample quality and prosody matter more than length. The project …
A machine learning math guide breaks down essential probability distributions for real-world deployment, covering Gaussian, Bernoulli, Binomial, and Multinomial distributions, and explains how concepts like temperature a…