AI Research

😸 WATCH: Robots That Learn Jobs by Watching You

How to Make AI Work for End-to-End Business Processes

From simplifying workflows to connecting knowledge and rules, coordinating AI agents, and delivering measurable business results. The post How to Make AI Work for End-to-End Business Processes appeared first on Towards…

Where a Cell Sits Matters More Than How Many There Are

Using spatstat raster layers and point process models to ask how neurons, astrocytes and microglia sit relative to each other The post Where a Cell Sits Matters More Than How Many There Are appeared first on Towards…

Building and Visualising Kolmogorov–Arnold Networks

Exploring what happens when neural networks learn functions instead of weights. The post Building and Visualising Kolmogorov–Arnold Networks appeared first on Towards Data Science.

Your RAG Pipeline Is Missing a 1994 Algorithm

Embeddings know that "broken" means "defective". They may not notice that ZX-4821 is not ZX-4812. The post Your RAG Pipeline Is Missing a 1994 Algorithm appeared first on Towards Data Science.

😺 Google launches Genie 4 with sound

Inside Mithril, the One-Employee Biotech Anthropic Acquired

Mithril Medicine had one full-time employee, supported by outside specialists and laboratories. Its acquisition by Anthropic offers a case study in how Claude can help coordinate drug research, with clinical progress…

Oracle AI Workspace Promises Business Workflows Through ChatGPT

Oracle and OpenAI want employees to access business data and complete approved workflows through ChatGPT. Individual Oracle plugins are listed for installation, while the complete AI Workspace experience remains under…

Everything That Happened in AI Today (Wednesday, October 28, 2026)

President Trump said the government will move away from the term “AI,” while OpenAI reportedly plans to buy Google TPUs. Anthropic also expanded Claude access across U.S. government agencies.

Dynamic Multi-Step Decoding for Time-Series Foundation Models

arXiv:2610.34409v1 Announce Type: new Abstract: Time-series forecasting models typically use a fixed decoding strategy at inference time: either one-shot prediction of the full horizon or autoregressive rollout over…

SCAFFOLD under Hessian Similarity: Sharp Convergence Rates

arXiv:2610.35663v1 Announce Type: new Abstract: One of the main challenges of federated learning is heterogeneous data split among the clients, leading to biased local updates called client drift. The SCAFFOLD algorithm…

On the stability of learning

arXiv:2610.35856v1 Announce Type: cross Abstract: Learning algorithms are usually analyzed under the assumption that informative gradients are continuously available. But this is not always true---learning signals in…

CoPE-CGL: Community-aware Prototype Extraction for Replay-Free Continual Graph Learning

arXiv:2610.35313v2 Announce Type: new Abstract: Continual graph learning (CGL) maintains models as graphs evolve without retraining from scratch, while mitigating catastrophic forgetting. Existing methods typically…

SATFormer: Learning When to Use Early Value Residuals in Transformers

arXiv:2605.03953v3 Announce Type: replace Abstract: Recent Transformer architectures expose later layers to representations computed in earlier layers, motivated by the observation that low-level features can become…

A Multimodal Machine Learning Framework Integrating Genomic, Epidemiological, Environmental, and Clinical Imaging Data for Accelerated Measles Detection and Transmission Inference

arXiv:2610.32996v1 Announce Type: cross Abstract: Background: Measles resurged in the United States during 2025-2026, with more than 4,600 reported cases. Timely detection and transmission inference require integrated…

High-resolution tactile observation makes hidden racket-control mechanisms learnable

arXiv:2610.35563v1 Announce Type: new Abstract: Experts can master fine hand-object manipulation skills, yet limited conscious perception of rapid tactile interactions hinders their ability to articulate the underlying…

Trust Region Continual Learning as an Implicit Meta-Learner

arXiv:2602.02417v3 Announce Type: replace Abstract: Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-based methods…

Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs

arXiv:2610.35280v1 Announce Type: cross Abstract: Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under…

The Noise-Transmission Burden of Diffusion Network: Why Image Prediction Can Outperform Noise Prediction

arXiv:2610.34834v1 Announce Type: cross Abstract: Clean-image prediction ($x$-prediction) and noise prediction yield equivalent population-optimal denoisers, yet can perform very differently in finite diffusion…

Uncertainty Evaluation to Support Safety of the Intended Functionality Analysis for Determining the Applicability of Performance Targets Across Triggering Conditions in ML-Based LiDAR Object Detection

arXiv:2610.35092v1 Announce Type: cross Abstract: For safety of the intended functionality (SOTIF) analysis according to ISO 21448, a machine learning object detector for light detection and ranging (LiDAR) point clouds…