Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A new unified variational framework for deep weakly supervised image segmentation uses a simplex-constrained Potts model with a smooth perimeter regularizer to create a convex, smooth energy functional that serves as a t…
Researchers introduce HyenaND, a subquadratic, global, input-dependent operator that acts directly on the native geometry of multidimensional data through convolutions with implicitly parametrized global, input-dependent…
A study by researchers on arXiv (2607.20301v1) finds that PortLLM, a training-free and data-free scheme for adapting large language models after continual pretraining, maintains long-term temporal portability across 10 c…
A new study from arXiv (2607.19382v1) finds that explainability methods such as attention rollout and Grad-CAM can reveal how continual learning models adapt to non-stationary time series, but also expose challenges in i…
Researchers propose STN-TGAT, a model integrating a temporal Transformer with a Graph Attention Network for stock ranking and portfolio construction, which outperforms benchmarks in predictive accuracy and investment pro…
Researchers propose Prefix-GRPO, a reinforcement learning framework that improves small language model agents by decomposing teacher trajectories into replay-aligned prefix queries and online continuations, enabling more…
A new study from arXiv introduces AdaRoPE, a method that assigns learnable rotation frequencies and attention scaling factors to each attention head in Transformers, outperforming standard Rotary Position Embedding (RoPE…
A new analysis of statistical label fusion in medical image segmentation finds that the widely used STAPLE algorithm often reduces to thresholded majority voting, suffers 95% EM suboptimality, and collapses under class i…
A new arXiv paper (2607.19573v1) formally defines structural generalization and proves that pure Transformers cannot learn it under the standard complexity assumption TC⁰ ≠ NC¹. The authors show that neuro-symbolic syste…
Researchers introduce Surrogate Latent Policy Optimization (SLPO), a method that brings outcome-reward reinforcement learning to autoregressive latent reasoners, enabling test-time scaling in latent reasoning without dec…
A regression-based approach to Arabic dialect geolocation that models dialectal variation as a continuous geographic space achieves a median localization error of 481.2 km under a leakage-free 5-fold GroupKFold protocol,…
A controlled comparison of language-specific versus cross-lingual knowledge graphs for implicit aspect identification in Arabic ABSA finds that a native Arabic KG outperforms a cross-lingual English KG by +0.199 micro-F1…
A benchmark study comparing standard non-confidential execution with confidential computing mode on a single NVIDIA H100 80GB GPU hosted in an Intel TDX confidential instance found that confidential mode increases averag…
Researchers propose Efficient Chain-of-Modality Reasoning (ECoM Reasoning), the first framework to introduce compressed reasoning into spoken language models (SLMs), improving reasoning accuracy by 21% over standard Chai…
Researchers propose Spectral-LSH, a training-free prompt compression method that uses Krylov subspace methods and SimHash to reduce long-prompt inference costs by grouping similar tokens into macro-tokens. On Qwen2.5-7B …
Researchers extended neural operator surrogate models for neutron flux estimation from one to two dimensions, testing Fourier neural operators (FNOs) and U-shaped neural operators (UNOs) on one-group transport with isotr…
A new study finds that orthogonalizing the mLSTM memory matrix at read time (five Newton-Schulz iterations, trained through) improves noisy associative recall by re-conditioning the learning problem during a training pla…
A new study from researchers using graph neural networks (GNNs) predicts groundwater arsenic concentrations across the United States, matching or outperforming gradient-boosted trees by accounting for spatial dependence.…
A 2.8M-parameter transformer achieves 0.01-bit entropy agreement with the Bayesian optimum for model selection in Bayesian wind tunnels using fixed-point-free involutions, but fails completely with opaque symbols when ar…
A new benchmark, Air Quality Arena (AQA), covers 6 pollutants over 3 years across 7 countries and 4 continents, with more than 14,000 station-pollutant series, and finds that time series foundation models (TSFMs) consist…