Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers at the Universities of Konstanz and Stuttgart have built a computer from a few hundred microscopic particles oscillating in a liquid, using their collective dynamics for reservoir computing. Led by Clemens Be…
A developer spent three months optimizing a ranking algorithm for a search system, only to realize the real problem was selection: the document that actually answered the user's question was never included in the candida…
Researchers Timo Bolkart, Daoye Wang, and Prashanth Chandran introduced SHELLS, a method for topologically consistent multi-view 3D head reconstruction using a DinoV2 backbone with LoRA adaptation and an XCiT-based trans…
Jharu v0.2.0, a free open-source disk cleaner and storage analyzer for macOS and Windows, targets gigabytes of junk left by development tools and machine learning frameworks. The tool identifies and safely removes ML mod…
Japanese researchers at the University of Electro-Communications and confectionery maker Ginza Cozy Corner have developed AI-powered robots that replicate the hand movements of skilled confectioners, aiming to preserve t…
NVIDIA Research's Efficient AI Team and Singapore Lab introduced SANA-Video 2.0, a hybrid video diffusion transformer at 5B and 14B scales that generates 720p video on a single H100 GPU. The model achieves a VBench score…
Machine-learning practitioner Enze Xie unveiled SANA-Video 2.0 on July 24, 2026, a full-stack optimized video model designed for efficiency and high quality. The system uses a hybrid attention architecture mixing dense 3…
ArmanddeCacqueray released SquareNet, an open-source tool that transforms wild elephant images into flat grids for machine learning preparation, as shown in a demonstration GIF on GitHub.
A developer shares 10 Python libraries essential for building AI applications in 2026, including FastAPI, LangChain, Pydantic, OpenAI SDK, ChromaDB, Pandas, NumPy, SQLAlchemy, Requests, and Rich. The developer emphasizes…
PyTorch users must ensure exact CUDA version matching between driver, toolkit, and framework to enable GPU acceleration, according to a technical guide on local CNN training. The guide details a three-step deployment flo…
Researchers have constructed a benchmark for webly supervised multi-label recognition (WS-MLR) including Web-COCO and Web-Pascal datasets, each containing about 300 thousand web images covering 80 and 20 categories respe…
Researchers have discovered that Mixture-of-Experts (MoE) routing in large language models functions as a form of Huffman coding, governed by a new Frequency-Diversity Law. The study, published on arXiv, shows that model…
Researchers present ODeform, a method extending Neural Ordinary Differential Equations to model continuous 4D dynamics of deformable objects in 3D space, eliminating discrete time steps while maintaining computational ef…
A new study from researchers at arXiv finds that the Muon optimizer's speedup in reaching the grokking threshold on modular arithmetic comes from orthogonalization via the Newton-Schulz iteration, not spectral-norm const…
Researchers introduced explanation-based runtime verification for ML-driven optical networks, an approach that uses model explanations to assess decision soundness before execution in the network control loop. The method…
A new method called GaugeQuant, introduced in a paper on arXiv, reduces perplexity in quantized large language models by learning quantization-optimal bases from internal symmetries during training. Using the LLaMA-2 7B …
Researchers have identified new polynomial-time tractable neural network architectures for training with ReLU and linear activation functions, pushing beyond previous state-of-the-art results. For ReLU networks, the team…
A new arXiv paper (2607.20533v1) proposes using neural predicates as a structured, probabilistic mechanism for generating investor views in the Black-Litterman portfolio construction model, replacing subjective uncertain…
Researchers propose Generative Bayesian Filtering (GBF), a filtering framework that replaces restrictive observation models with pretrained conditional generative models parametrized by conditional variational autoencode…
Axolotl3D, a multi-modal and occlusion-aware 3D generation model introduced in arXiv:2607.20660v1, jointly conditions on images, visibility masks, camera parameters, and a partial point cloud to enable faithful 3D shape …