Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A developer outlined how diffusion models generate data by first defining a forward diffusion process that progressively corrupts real samples with Gaussian noise, then learning a reverse diffusion process that moves fro…
Figure AI unveiled Helix 2.5, a new neural network for humanoid robots, on September 17, 2026, demonstrating robots performing extended household chores such as tidying, towel folding, and bed making in 30 homes where no…
Figure AI unveiled Helix 2.5 on September 17, 2026, a humanoid neural network that achieved a 56% success rate across 237 completed tasks out of 420 attempts in 30 Bay Area homes its robots had never entered, using a sin…
Groundcover is evaluating TypeSafe's newly released Jev model for AI observability, testing whether its parallel-sampler architecture and reinforcement learning for calibrated decisions can classify agent trace outcomes …
Qualcomm has patented a machine learning pipeline that trains a model on data from two separate network simulators to predict wireless network performance metrics — throughput, latency, and signal reliability — before ha…
Forbes contributor Lance Eliot published an analysis of newly announced reinforcement learning with calibrated decisions (RLCD), cautioning readers to look past the AI headlines and hype surrounding the technique. The pi…
Qdrant researchers found that multilingual embedding models group text by language as well as meaning, causing same-language answers to appear in the top 10 in 61% of cases on the 15,277-article, five-language XRAG datas…
A paper posted to arXiv on 19 May 2026 finds that for large-model pretraining in the high-compute, data-scarce regime, the best data filter is no data filter. The scaling studies report that sufficiently trained large-pa…
A new arXiv paper (arXiv:2609.19213v1) introduces layer-wise curriculum learning for efficient LLM compression, a method that partitions a model into multi-layer segments to transfer knowledge from teacher to student mod…
A new arXiv paper (arXiv:2609.19209v1) proposes an Intent-Driven Query Suggestion Framework that combines intent-aware diversity modeling with query-level credit assignment to generate follow-up query slates. The framewo…
A non-equilibrium dynamical mean-field theory (DMFT) developed by researchers describes how learning in recurrent neural networks drives a transition from chaotic to stable task-dependent dynamics, according to a paper p…
Researchers introduced block parallelism (BP) and context-sharded block parallelism (CSBP), new distributed parallelism dimensions for training block diffusion language models (BDLMs) on long contexts, reporting throughp…
Researchers introduced radio-frequency convolutional neural networks (RF-CNNs), which repurpose the frequency mixer in existing wireless radios to perform CNN inference, according to a paper published as arXiv:2609.19279…
Researchers introduced Personalized Federated Hierarchical Gaussian Processes (pFedHGP), a federated learning method that decomposes each client's latent function into a shared global component, a client-specific deviati…
A new technique called probe guidance, introduced in arXiv paper 2609.19356v1, uses the frozen internal states of an existing diffusion model to construct a guidance signal, eliminating the extra forward pass required at…
Researchers introduced FCx (Feasible Counterfactual Explanations), an algorithm that generates counterfactual explanations which are realistic, low-cost and feasible, according to a paper published on arXiv as 2609.19383…
A leakage-safe Bernoulli/Categorical Naive Bayes classifier identified I-309 (CCL1) as the dominant incremental predictor of cognitive impairment in the Panama Aging Research Initiative--Health Disparities (PARI-HD) coho…
Researchers proposed Reward Stimulation Implicit Q-Learning (RSIQL), a non-hierarchical offline goal-conditioned reinforcement learning method that adds reward signals at progress-making intermediate states identified by…
Researchers developed three methods that use large language models to incorporate rich auxiliary information into Bayesian Optimization, according to arXiv paper 2609.19437v1. The methods consistently outperformed both s…
A new arXiv paper (2609.19476v1) reports a latent space Bayesian optimization method that achieves at least a 100x speedup over state-of-the-art baselines while matching or improving performance on molecular and image ge…