Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A developer's blog post explains how CatBoost's ordered target statistics prevent target leakage in categorical feature encoding, a common issue in tabular machine learning. The post illustrates the problem with an analo…
Rockwell Automation announced on August 11 an API-enabled integration between its Plex Quality Management System (QMS) and FactoryTalk Analytics VisionAI, bringing AI-based visual inspection results into quality-manageme…
A new thesis introduces scalable tools for nested optimization in deep learning, addressing bilevel problems such as hyperparameter optimization and generative adversarial networks, where classical methods fail at scale.
Researchers propose JacNet, a neural network architecture that directly learns the Jacobian of an input-output function, enabling easy enforcement of structural priors such as invertibility and k-Lipschitz continuity. Th…
Temple Compute released Pantheon, a collection of production-ready scientific workflows for its Horus Runtime, covering molecular dynamics, virtual screening, docking, and LLM training. The workflows are multi-stage pipe…
A new study from researchers demonstrates that large language models (LLMs) can match or outperform traditional hyperparameter optimization (HPO) methods such as Bayesian optimization within constrained search budgets. B…
A team at Cua has developed a process-scoped Metal capability shim that unlocks 11-16x faster LLM inference in macOS virtual machines on Apple Silicon, bringing VM performance to 94-99% of bare-metal speeds. The bottlene…
A 32-attempt Claude Code evaluation on August 11, 2026, found that Langfuse was selected in every tracing and production-monitoring task but in none of the prompt comparison and release-gate tasks. However, the analysis …
Tynx, a new ONNX runtime with a PyTorch-shaped API for inference and training, has been released as a Python package under 20 MB. Written in Rust, it uses Burn/CubeCL and wgpu for GPU execution across operating systems a…
A new study finds that most performance gains from harness evolution—automated optimization of the prompts, tools, and control flow around a fixed LLM—are driven by overfitting to the search set or by spending more infer…
Xiaomi Inc.'s MiLM Plus team released PROVE, a perception-aligned evaluation framework for object removal, at ACM MM 2026, featuring two metrics—RC-S for spatial coherence and RC-T for temporal consistency—and a real-wor…
A developer built a snapshot regression suite for LLM outputs after a free-tier model was silently updated, degrading results without any code changes. The tool, drift_check.py, records baseline semantic content and comp…
Researchers introduced Boundary-Seeking Policy Gradient (BSPG), a first-order method for safe reinforcement learning that drives policies to the constraint boundary when constraints are active, achieving a finite-horizon…
Researchers from an unnamed institution propose an EM-based algorithm, BoRa_EM, that jointly learns item rewards and worker reliability from pairwise comparisons under a Boltzmann-rational model, using Polya-Gamma latent…
TRACE-GS, a new framework from arXiv (paper 2608.10286v1), performs on-policy trajectory distillation with privileged geometric conditioning to improve sparse-view 3D Gaussian Splatting (3DGS) restoration. It uses a teac…
Researchers propose MD-ProTector, a new method for detecting LLM-generated text that uses multiple trainable reference vectors, or prototypes, per class to capture within-class variation. Evaluated on three benchmarks (M…
Researchers propose SeFaR, a framework for semantic-feature-centric testing of deep neural networks, which uses diffusion and vision-language models to generate photorealistic perturbations and identify failure-inducing …
Researchers introduce ChronoSSM, an autoregressive State Space Model that jointly models events and timestamps with a shared backbone trained using combined token and temporal generation objectives. Across four domains, …
A new study finds that JPEG2000 compression at a 20:1 ratio preserves the quality of 3D brain MRI generative models, with synthesis quality statistically equivalent to uncompressed training (mean PSNR 27.3 dB vs. 27.0 dB…
LinkedIn researchers report that a decision-centric causal optimization framework for large-scale targeting and recommendation delivered a statistically significant +7.20% lift in the primary long-term-value metric in an…