Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers using the CL1 closed-loop electrophysiology platform found that modular cortical cultures of human iPSC-derived neurons significantly outperformed unconstrained monolayers and 3D organoids on a spatio-tempora…
Linux 7.2 has been released, introducing Cache Aware Scheduling after more than a year of work, along with AMD Zen 6 prep, HDMI 2.1 Fixed Rate Link support, and initial support for 2023 MacBooks. The kernel also adds AMD…
PixelRAG, an open-source visual retrieval-augmented generation tool, treats documents as screenshots to preserve layout and structure for AI models. The project, built by StarTrail-org, includes components for rendering,…
Open-source marketing mix modeling (OS-MMM) packages such as Google's Meridian, Meta's Robyn, and PyMC Marketing are gaining traction as privacy changes like GDPR, COPPA, and Apple's IDFA deprecation make attribution les…
Five researchers posted a preprint on arXiv on 11 August 2026 proposing a label-free method to evaluate agentic continual learning harnesses by measuring how much a smaller student model converges toward a stronger teach…
Researchers propose Multiphase-Diff, a diffusion-based generative model for high-contrast multiphase physical systems with sharp interfaces, addressing three coupled difficulties: singular gradient terms at coefficient j…
A new arXiv study (2608.13729v1) finds that synthetic image generation from diffusion-based models fails to consistently improve downstream classifier performance over non-generative augmentation in specialized, data-sca…
Researchers introduced CAST (Closed-form Analytic Semantic Transfer), a training-free, image-free framework that extends pre-trained classifiers to unseen classes via weight injection, achieving performance comparable to…
A new diagnostic framework called ChartProbe, introduced in an arXiv paper (arXiv:2608.13766v1), shows that vision-language models (VLMs) can improve complex visual reasoning by training on simpler skills—perception, gro…
A study evaluating Kolmogorov-Arnold networks for land classification from Landsat 8 imagery found that the KAN matched random forest accuracy and outperformed multilayer perceptrons on an independent Calgary, Alberta da…
A new arXiv preprint (2608.13889v1) presents a consensus-gated multi-agent neural architecture search (NAS) system that uses three large language models (Claude, GPT-5.1, and Gemini 2.5 Pro) to debate and author candidat…
Researchers propose CoANeRV, a coordinate-aware token-space framework for amortized video representation that forms compact video tokens in one feed-forward pass and uses a shared coordinate-conditioned decoder, avoiding…
Researchers introduced CMCNet, a model that aligns ultrasound image embeddings with textual TI-RADS representations for fine-grained thyroid classification, achieving superior performance over InfoNCE, center loss, multi…
Researchers propose a fast implicit neural light field representation that decomposes a 4D light field into horizontal disparity, spatial texture, and vertical disparity planes, each represented by multi-resolution low-r…
Researchers introduced MobileMem, a benchmark and framework for studying on-device long-term memory in AI agents, grounded in a year-scale collection of mobile experiences. It uses a knowledge-grounded synthesis pipeline…
A new arXiv paper (2608.13621v1) reveals that the Predictive Information Bottleneck VJEPA (PIB-VJEPA) model is mathematically equivalent to a hidden Markov model (HMM), with its stochastic context encoder acting as an am…
A new arXiv paper (2608.13608v1) proposes a label-free framework for evaluating agentic continual learning harnesses in cybersecurity, using teacher-relative convergence as a proxy for true uplift. The authors show that …
A new expert-guided neuro-symbolic pipeline that combines a large language model with a Sugeno fuzzy inference system to assess compliance with sepsis treatment protocols found that antibiotic timing is the most critical…
Researchers introduced a novel automata-based approach for reinforcement learning from Signal Temporal Logic (STL) specifications, constructing a timed alternating automaton to provide efficient memory and Markovian rewa…
Researchers introduced the Lorentzian Fourier Neural Operator (L-FNO), a stochastic neural operator combining an FNO-style covariate path, Lorentzian spectral kernels, and likelihood-based training, to model rare, bursty…