← 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.

6,183 stories · RSS feed

arXiv Machine Learning
Sep 24

Advances in Diffusion-Based Generative Compression

This article reviews recent diffusion‑based methods for generative lossy image compression, highlighting how these techniques encode a source into an embedding and use a diffusion model to iteratively refine the reconstruction during decoding. It discusses the role of auxiliary entropy models for transmitting the embedding, explores the use of diffusion models for information transmission via channel simulation, and frames the discussion within rate‑distortion‑perception theory, common randomness, and inverse‑problem connections. The review also identifies open challenges in the field.

By Yibo Yang, Stephan Mandt
ragdiffusion
More like this →
arXiv Computation and Language
Sep 24

Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models

The paper introduces RoPA Manager, a system that automates the extraction of Records of Processing Activities (RoPA) required by Vietnam’s new Personal Data Protection Law. It combines hybrid retrieval techniques—lexical ranking, dense‑vector search, and Reciprocal Rank Fusion—with locally deployed large language models to avoid data‑sovereignty issues. A Vietnamese RoPA benchmark of 32 organizations and 77 processing activities was created, and the system achieved robust scorer performance (F1 ≈ 0.95) and moderate end‑to‑end token coverage (≈ 50‑55%).

By To Duy Hinh, Nguyen Le Quoc Anh, Phan Van Tri, Khuong Nguyen-An
llmsragbenchmarks
More like this →
arXiv Computation and Language
Sep 24

Computation Over Geometry: Meaning Identity Is Computed, Not Shipped in the Embeddings

The paper argues that meaning identity—whether two sentences convey the same idea after wording changes—is not encoded in the geometry of independently produced sentence embeddings. Experiments on frozen off‑the‑shelf encoders and language models show that identity can only be reliably computed when both sentences are processed together in a single forward pass, yielding high accuracy (0.90–0.96) on PAWS‑X, whereas independent embeddings or simple fusion methods perform near chance. Even advanced bi‑encoder fine‑tuning improves performance on PAWS but fails to generalize to other similarity tasks, underscoring that identity is a cheap computed operator rather than a property of individual sentence vectors.

By Jiaqi Deng
llmsragfine-tuning
More like this →
arXiv Computer Vision
Sep 24

Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models

The paper introduces "open‑set adversarial forgetting" to make selected identities unlinkable in face recognition models while keeping the system functional for other users. Three loss functions are proposed: one disperses embeddings from their centroid, and two map each image to a near‑orthogonal target—either learned via the classifier head or fixed as an almost‑orthonormal frame. Experiments on multiple backbones and forget scales show that these losses, especially the orthonormal‑frame approach, effectively render the targeted identities unidentifiable and outperform prior methods while preserving higher retain rates.

By \"Unsal \"Ozt\"urk, Vedrana Krivoku\'ca Hahn, Sushil Bhattacharjee, S\'ebastien Marcel
ragfine-tuningsafety
More like this →
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 →