← Back to all news

Retrieval-augmented generation

Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.

6,299 stories · RSS feed

arXiv Machine Learning
Sep 24

Geospatial embeddings detect old-growth forests but buffered spatial validation narrows their advantage over Sentinel features

arXiv:2609.28194v1 Announce Type: new Abstract: Old-growth forests develop over centuries under minimal anthropogenic disturbance, producing structurally complex and biodiverse stands. In Europe, pro...

By Thomas Ratsakatika (Department of Geography, University of Cambridge, Cambridge, UK), Mihai Zotta (Fundatia Conservation Carpathia, Brasov, Romania), Srinivasan Keshav (Department of Computer Science and Technology, University of Cambridge, Cambridge, UK), Emily R. Lines (Department of Geography, University of Cambridge, Cambridge, UK)
rag
More like this →
arXiv Machine Learning
Sep 24

Anomaly-Free Self-Optimization via AUC Bounds

arXiv:2609.27362v1 Announce Type: new Abstract: Anomalies are rare, and anomalous data are often unavailable during development, making it difficult to determine which anomaly detection models and co...

By Kevin Wilkinghoff, Zheng-Hua Tan
rag
More like this →
arXiv AI
Sep 24

ProteinJEPA: Latent prediction improves protein language model pretraining

ProteinJEPA introduces a joint‑embedding predictive architecture that supplements masked language modeling (MLM) with a cosine loss to predict latent representations of a teacher model. On 19 protein tasks, MLM+JEPA outperforms compute‑matched and step‑matched MLM‑only training across 78 and 76 of 114 comparisons, achieving notable gains on structure‑ and homology‑sensitive tasks such as SCOPe‑40 retrieval and remote homology. Ablation studies show the cosine loss is superior to mean squared error and that latent prediction complements rather than replaces MLM.

By Dan Ofer, Dafna Shahaf, Michal Linial
llmsrag
More like this →
arXiv Machine Learning
Sep 24

Pheno-GS: Phenoscape-scale Geodesic Sinkhorn

Pheno-GS is a new method for computing scalable, geometry-aware optimal transport distances between large patient cohorts of single‑cell data. It uses graph connectivity regularization, an unbalanced OT formulation with KL marginal penalties, and a batched matrix algorithm that dramatically speeds up pairwise distance calculations. The authors validate the approach on synthetic benchmarks and a CyTOF perturbation dataset.

By Alistair Wilkinson, Christopher J. Tape, Smita Krishnaswamy
ragdiffusionefficiencybenchmarks
More like this →
arXiv Machine Learning
Sep 24

Quantifying the Occult: A Comparative Study of Hindu and Buddhist Deities Using Machine Learning Methods

The paper presents a dual‑matrix computational framework that quantifies morphological and theological differences among 196 Hindu and Vajrayana Buddhist esoteric deities. It uses a Gower distance matrix with a new Cardinality Weighting algorithm for physical form and dense vector embeddings from LLMs for theological function, revealing how visual forms can mask shared functions and how high‑cardinality symbols cluster orthodox and Tantric entities. The study demonstrates near‑identical coordinates for the Hindu Chinnamasta and Buddhist Chinnamunda, and releases the architecture as an open‑source tool for Digital Humanities research.

By Ankit Bhattacharjee
llmsragmultimodalbenchmarkssafety
More like this →
arXiv Computation and Language
Sep 24

UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation

UniDataAgent (UniDataAgent) is an ontology‑grounded system designed to automate enterprise question‑to‑report tasks while preserving organization‑specific semantics. It separates semantic acquisition from online execution, with an Ontology Acquisition and Validation (OAV) stage that builds versioned ontologies from metadata, business knowledge, and expert input, and a Question‑to‑Report Execution (QRE) stage that retrieves semantic contracts, coordinates skills and data tools, validates results, and produces evidence‑linked reports. In a deployment across 27 enterprise tables and thousands of metric types, ontology construction took a few hours versus a week manually, and report generation took minutes versus several working days, achieving 95.0% strict accuracy on real business questions compared to 72.5% for document RAG.

By Yutai Duan, Yahui Zhao, Zhangti Li, Yu Ma, Zhenfeng Qi, Shaoyang Yuan, Jing Fan, Jie Liu
ragagents
More like this →
arXiv AI
Sep 23

Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors

Tactile-JEPA is a self‑supervised pre‑training method for distributed tactile sensors that leverages the sensors’ spatial topology to learn topology‑aware representations. It predicts embeddings of masked sensing elements using a sensor connectivity graph and dual‑scale masking to capture both local contact details and the global tactile surface state. Evaluated on three diverse datasets, it improves force estimation by 6.3 % and in‑hand orientation error by 20.8 % over previous state‑of‑the‑art methods, and yields consistent gains in downstream tasks such as policy learning.

By Elizaveta Kovtun, Matvey Konovalov, Andrey Sakhovskiy, Semen Budennyy
ragroboticsbenchmarks
More like this →
arXiv Machine Learning
Sep 23

On the Effect of Bit-Level Parameter Perturbations in Machine Learning and Deep Learning Models

The paper studies how small, targeted changes to model parameters affect classical machine learning models (HMM and SVM) versus deep learning models (MLP and LSTM). Using the Drebin Android malware dataset, it finds that classical models are brittle, with a few parameter changes dramatically altering behavior, and have limited steganographic capacity. In contrast, neural networks are parameter‑redundant, allowing many parameters to be altered with minimal impact, thus supporting higher steganographic capacity.

By Akanksha Raghapur, Mark Stamp
rag
More like this →