Machine Learning News

A new inference-time framework, Adjudicated Captioning, achieves CIDEr 117.6 and SPICE 21.9 on the COCO Karpathy test split for zero-shot image captioning, up from 108.0 and 20.3 for the baseline IFCap, a +9.6 CIDEr gain…

Researchers introduced an amortized Bayesian experimental design framework for cognitive planning experiments, treating the experimental environment as a design variable to optimize parameter inference. On the Mouselab-M…

Researchers from the University of Washington evaluated Koopman-based upsampling techniques using dynamic mode decomposition (DMD), extended DMD (EDMD), and optimized DMD to improve sparse identification of nonlinear dyn…

Researchers propose ReLoop-UME, a universal multimodal embedding model that recurrently reuses a parameter-shared retrieval-forming block with Learnable Retrieval Registers, improving retrieval on MMEB-V2 and MRMR while …

Researchers introduced LARA (Lightweight Additive Residual Adaptation), a method that adapts frozen AI models by adding low-rank corrections to the residual stream instead of modifying weights, matching LoRA's performanc…

Researchers propose a new unsupervised data augmentation method combining Gaussian Mixture Models (GMMs) and Large Language Models (LLMs) to improve clustering of underrepresented topics in imbalanced text datasets. The …

A new arXiv preprint (2607.28667v1) proves that classifying large language models (LLMs) by modeling token embeddings as trajectories of a black-box dynamical system (DS) achieves misclassification probability that decay…

A study by researchers evaluating GRU, LSTM, and Transformer encoder models for classifying Level 2 automated driving systems (Comma Openpilot, Tesla Autopilot, Cadillac Super Cruise) from vehicle telematics data found t…

Researchers introduced TAGTorch, an open-source PyTorch-based library that unifies tools for geometry, topology, and symmetry-aware machine learning, addressing the fragmented software ecosystem in this area. The library…

Researchers introduced the Coarse-Fine Transport Distance (CFTD), a distribution-based evaluation framework using atom-averaged features from pretrained Machine-Learning Interatomic Potentials (MLIPs) such as MACE, to as…

A new arXiv study (arXiv:2607.28707v1) finds that entropy-based pruning offers no advantage over random pruning for compressing Chain-of-Thought (CoT) reasoning in large reasoning models, and that retaining low-entropy t…

Researchers propose MARS, a Monte Carlo Tree Search-based framework for automatically repairing multi-agent systems, and introduce StateMAS, a benchmark with 1,310 replayable failure trajectories. On StateMAS, MARS outpe…

Researchers introduced embedder-centric learning (ECL), a framework unifying few-shot, continual, zero-shot, and in-context learning for on-device adaptation at the edge, achieving state-of-the-art results in character r…

Researchers proposed an automated classification method for COVID-19 cases from chest CT volumes using a 2D/3D hybrid convolutional neural network (CNN) designed for anisotropic volumes. The method achieved an average cl…

A new arXiv preprint (2607.29120v1) finds that curriculum design and synthetic data diversity matter more for relational Prior-Data Fitted Networks (PFNs) than the specific generator or scale. Using the PluRel generator,…

A scoping review of 190 studies on machine learning for surgical risk stratification and outcome prediction using electronic health records found that most relied on single-center private datasets, with limited data moda…

Researchers introduced FairDiffuseVQVAE, a two-stage tabular diffusion model that achieves fairness by construction through uniform sampling of the protected attribute at inference time, decoupling fidelity from fairness…

Researchers introduced SILVA Networks, a new implicit neural architecture that separates stimulus, local interaction, global interaction, damping, and readout within a fixed-point update, allowing for clearer identificat…

Researchers introduced Gated Q-learning, a new algorithm that smoothly interpolates between Watkins' Q(λ) and Peng's Q(λ) to manage off-policy bias in multistep credit assignment for reinforcement learning. The method us…

Researchers at an undisclosed institution developed a value-based reinforcement-learning framework using graph neural networks to optimize dynamic matching markets, proving an event-time reduction and reducing the learne…