Community feed
A focused stream of recent stories from the sources curated for this community. Latest: QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting, Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model, and Event-Driven ML Pipeline Orchestration for Manufacturing: An AWS Industry Experience. Page 117.
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06936: QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06931: Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06890: Event-Driven ML Pipeline Orchestration for Manufacturing: An AWS Industry Experience
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06881: Comparative review of hybrid forecasting models for short-term prediction of building thermal load
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06861: When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06855: TEMPEST: Temporal Embeddings for Scalable Driver Identification via Angular Margin Learning
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06991: State-Aware Interaction MIL for Rare Joint Molecular Phenotype Prediction in Colorectal Cancer and Lung Adenocarcinoma
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06960: DistScene: Object-to-Scene Distillation for 3D Scene Generation
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06938: UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation
Planet AI Developer Filter
Abstract page for arXiv paper 2610.07032: Investigating Model Compression for Neural Machine Translation in the Biomedical Domain
Planet AI Developer Filter
Abstract page for arXiv paper 2610.07019: Calibrated Answers About Randomized Trials From a 4-Billion-Parameter Open Model: A Registered Test and a License-Clean Release
Planet AI Developer Filter
Abstract page for arXiv paper 2610.06962: Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery?