Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Gartner's 2017 Data & Analytics Summit found that 74% of organizations had descriptive analytics capabilities, 34% had diagnostic, 11% had predictive, and only 1% had prescriptive, highlighting a widespread overestimatio…
AI-powered tools are transforming patient-reported outcomes (PROs) in clinical research by automating data collection, cleaning, standardization, and regulatory submission preparation, according to Made AI. These technol…
Freshworks Inc. is hiring a Lead Data Scientist in Bengaluru, India, to lead GenAI initiatives for its employee and customer experience products, targeting a conversational servicebot for 1 million+ monthly active users.…
Arc Institute opened pre-registration for its 2026 Virtual Cell Challenge, which will require AI models to predict gene-knockdown responses across multiple cell lines without task-specific examples, a harder zero-shot te…
PassiveDx, a personal health anomaly detection layer, learns an individual's behavioral and physiological baseline from passive signals such as typing, motion, and sleep, and flags deviations over time. The system, desig…
Researchers introduced GradCuit, a test-time method that improves LLM reasoning by inserting optimizable latent vectors at an intermediate Transformer layer, using causal self-attention as a differentiable circuit to flo…
A study by Michael Timothy Bennett, submitted to arXiv on January 30, 2023, and revised April 11, 2024, argues that the optimal hypothesis for generalization is the weakest, not the shortest, and that compression is neit…
A developer trained a small language model from scratch on an $8 ESP32-S3 microcontroller, demonstrating that training, not just inference, is possible on ultra-low-cost hardware. The project, inspired by the esp32-ai re…
Researchers propose Convex Hull Neighborhood Smooth Dual Generalization (CSDG), a new offline reinforcement learning method that explicitly separates in-sample value targets from local out-of-distribution corrections, ac…
Researchers at an undisclosed institution introduced a pipeline that uses a language model to automatically group features and MLP neurons into supernodes for circuit tracing, matching human annotator interpretability. O…
Researchers introduced p-SpheretNorm, a one-parameter family of angular retractions for spherical residual streams in deep neural networks, showing that the exponential map used in Geodesic Normalization (GeoNorm) is jus…
Researchers propose NOMADD, a post-hoc method to reduce concept drift in tabular models, applicable to trees, neural networks, and tabular foundation models. On the 18-dataset Drift-Resilient TabPFN benchmark, NOMADD imp…
Researchers propose CHASE (Classification with Hierarchical Analysis and Structured Enforcement), a single-stage framework that uses a clinically driven three-level taxonomy of 9 anatomical regions, 17 sub-regions, and 2…
Researchers introduced DiffImaginE, a multimodal named entity recognition (MNER) verifier that formulates type verification as conditional latent diffusion inference, replacing deterministic imagine-and-compare methods. …
A new arXiv preprint (2608.02829) finds that converting a pretrained 1.4B-parameter Pythia model into a 410M-parameter sibling works best through initialization transfer, not weight projection. The authors show that dens…
Researchers introduced Group-Relative Preference Backpropagation (GRPB), a method that converts same-task rankings into zero-sum advantages to train long-horizon video editing agents, and released the resulting 9B Crayot…
Researchers developed a multimodal auto-regressive transformer surrogate to model variable well operations and quantify uncertainty in geological carbon storage, achieving a median saturation MAE of 0.028 and median rela…
Researchers introduced GeoID-PINN, a physics-informed neural network for regional epidemic inference, which in a four-region simulation achieved source-composition error 0.099 with a compatible distance prior, versus 0.5…
A new arXiv paper (2608.02975v1) introduces TQLite, a distillation framework that uses a multi-LRM jury to train small language models (SLMs) for MQM-based translation quality evaluation, achieving performance far exceed…
Researchers introduced CT-HEG, a bidirectional, timestamp-attributed event graph for ICU in-hospital mortality prediction, and their CHIRP-Net model achieved a 5-seed mean AUROC of 0.8449±0.0071 on MIMIC-IV v3.1 (31,142 …