Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers from Southeast University propose RAID, a new AI-generated image detection method that uses bit-reversed images and a gradient-based patch selection with a convolutional classifier, achieving state-of-the-art…
Researchers introduced TokenSwap, a method that replaces textual concepts with semantically aligned images to create image-interleaved inputs, and found that across 42 multimodal large language models, performance droppe…
A new study from arXiv (arXiv:2607.28658v1) finds that downstream fine-tuning on GLUE does not reliably preserve the reference ranking of federated pre-trained models, whereas direct next-token prediction on GLUE text st…
Researchers introduced TELLER, a dual-path iterative preference optimization method for table entity linking, which improves accuracy on the TableInstruct entity-linking subset from 94.35% to 94.50% via a direct-answer p…
Researchers from the Applied Machine Learning Lab propose GenCDSR, a generative framework for cross-domain sequential recommendation that improves average accuracy by 1.5% and reduces inference latency by 85.1% over stat…
Researchers proposed Step-Aware Reasoning Energy (SARE), a geometric framework that quantifies computational effort at individual chain-of-thought steps using Centered Kernel Alignment between token hidden states, reveal…
Researchers propose ViSAGE, a multimodal agentic memory framework that constructs self-correcting, entity-centric memories for long-form video understanding, outperforming the strongest baseline by 5.9% in accuracy. The …
Researchers introduced EarlyDx, a benchmark built from 154,834 emergency department encounters in MIMIC-IV, to evaluate open-ended early diagnosis at hospital admission. The study found that no evaluated system, includin…
Researchers propose SAF, a Stable Advantage Fusion framework that combines reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) for training language models, addressing magnitude and tem…
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…
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 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…
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 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 DFSC, a PyTorch environment for fractional scientific machine learning that uses the Mittag-Leffler Spectral Layer to separate known fractional propagation from data-driven corrections, enabling jo…
Researchers introduced implicit machine learning force fields (I-MLFFs) that replace explicit neural network layers with self-consistent fixed-point equations, enabling two- to five-fold reductions in compute and memory …
Researchers propose new search methods for Branch and Bound (BaB) neural network verification that locate verdict boundaries more efficiently by exploiting path monotonicity and splitting multiple activation functions si…
Researchers propose history-enriched rollout training (HERO), a method that augments conventional absolute trajectory supervision with relative supervision derived from the model's optimization history to stabilize long-…
Researchers introduced SERUM, a multi-pass framework that extracts finite-state behavioral models from unstructured egocentric video using hierarchical VLM annotation, achieving lower perplexity and higher action predict…
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…