Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A new paper on arXiv (submitted July 23, 2026) provides an overview of Bayesian and frequentist simulation-based inference (SBI) with machine learning, covering methods such as neural posterior estimation and neural like…
A new study from researchers at an undisclosed institution uses machine learning to analyze toxic behavior on the decentralized social platform Mastodon, finding that the lack of unified moderation standards across indep…
A single DINOv3-pretrained ConvNeXt trained with a tuned recipe achieves 88.19 mAP on VeRi-Wild Small and 77.47 mAP on VeRi-Wild Large for vehicle re-identification, matching the strongest multi-branch baseline. Research…
Researchers propose Visual Saliency Steering Distillation (VSSD) to improve multimodal chain-of-thought reasoning in small models by using attention maps from multimodal large language models to generate perturbed images…
Researchers propose Risk-routed Implicit Boundary Refinement (RIBR), a compact segmentation framework that uses implicit neural representation as a risk-routed residual correction for robust ultrasound image segmentation…
A new study from arXiv (2607.22039v1) finds that reinforcement learning (RL) significantly reduces task conflicts and performance degradation in large language models (LLMs) during model merging, compared to supervised f…
A new study from researchers testing the quadratic model of optimization on a 150M-parameter LLM trained on 3B tokens finds that the simple model can predict optimization dynamics over windows lasting up to 10% of traini…
A new quantum federated learning framework called DUQFL-Prox, proposed in arXiv:2607.21647v1, improves stability, generalization, and client fairness in privacy-sensitive distributed decision systems such as fraud detect…
A new study from arXiv presents a partial-identification approach to bounding the causal effect of a new ML model using prior randomized control trial data, leveraging assumptions about counterfactual correctness and sub…
A new pipeline using large language models to extract grammatical rules and lexicons from grammar books generates synthetic parallel corpora for fine-tuning machine translation models, improving over seed-data baselines …
Researchers propose EVL-MCoT, an enhanced vision-language multi-chain-of-thought approach for harmful meme detection, achieving promising results on the HatefulMemes and MultiOff datasets. The method addresses limitation…
Researchers propose TextSLIP, a medical vision-language pretraining framework that augments CLIP with intra-modal text contrastive learning to improve fine-grained semantic supervision for radiology report generation. Pr…
A systematic review of 60 studies on diffusion models for medical image inpainting finds that denoising diffusion probabilistic models and latent diffusion models are the dominant architectures, primarily used for artifa…
Researchers propose the Semantic Gaussian Allocation Transformer (SAGFormer), which uses Gaussian attributes and local geometric-semantic features to score candidates and select a fixed final Gaussian set for 3D semantic…
Researchers propose SCALE, a self-supervised constraint-aware layout generation framework for local place-and-route design-rule violation fixing at sub-2nm nodes, boosting state-of-the-art agents' solve rates by +12–25% …
Researchers propose CARNet, a Cycle-Conditioned Core Aggregation and Redistribution framework for multivariate time series forecasting that integrates global recurrent cycle information into efficient core-based interact…
A new Bayesian framework called Neural Atom Prevalence (NAP) achieves state-of-the-art structural sparsity in feedforward neural networks, reducing active nodes to as few as 8% of the original dense architecture on MNIST…
Monotone FedNAM, a physically constrained federated additive model, eliminates all monotonicity violations in SLA-risk prediction for O-RAN, raising constrained shape consistency from 0.71 to 1.00 and reducing uplink tra…
NVIDIA researchers introduced Molt, an open-source PyTorch-native training framework for agentic reinforcement learning that is compact enough for a single researcher to understand and modify end to end. Under a matched …
Researchers present EaaS, a cloud-native reference architecture that operationalizes AI evaluation methods as six stateless Kubernetes microservices, achieving sub-2ms p99 latency for conformal prediction and calibration…