Retrieval-augmented generation

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

6,643 stories · RSS feed

arXiv Machine Learning

Jun 29

Forecasting Technological Directions in Wireless Networks and Mobile Computing via AutoML Framework

arXiv:2606. 27394v1 Announce Type: cross Abstract: The exponential increase in scientific publications has driven the emergence of new trends.

By Ahmed Abolfadl, Marwa Mahmoud, Basma Afifi, Mervat Abu-Elkheir, Maggie Mashaly

llms rag

arXiv AI

Jun 29

SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval

arXiv:2606. 27976v1 Announce Type: cross Abstract: Dense embeddings underpin semantic search and RAG, yet a leaked vector store hands much of the underlying text back to whoever holds it.

By Sergey Kurilenko

rag safety

arXiv AI

Jun 29

DG^VoiC: Speaker Clustering for Fraud Investigation under Real Call-Centre Conditions

arXiv:2606. 28048v1 Announce Type: cross Abstract: Insurance fraud remains costly and operationally difficult, particularly in call-centre workflows where many customer interactions begin at FNOL.

By Muhammad Shakeel Akram, Amal Htait, Abdul Hamid Sadka, Emma Meisingseth, Karishma Jaitly

rag

arXiv Machine Learning

Jun 29

Quantum Dynamic Time Warping for Multivariate Time Series Classification

arXiv:2606. 27815v1 Announce Type: cross Abstract: Dynamic Time Warping (DTW) is a cornerstone for time series classification, but its reliance on Euclidean distances fails to capture latent cross-channel correlations in complex multivariate data.

By Diego Alvarez-Estevez, Alejandro Mayorga-Redondo, Eduardo Mosqueira-Rey

rag benchmarks safety

arXiv AI

Jun 29

VASAE: Naming SAE Dictionary Directions with Vocabulary-Aligned Anchoring

arXiv:2606. 27941v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) provide useful decompositions of Transformer residual streams, but their learned features are usually named post hoc rather than directly connected to the Transformer's token vocabulary.

By Kairui Zhang, Ziwen Yu, Zahraa S. Abdallah, Martha Lewis

llms rag safety

arXiv Machine Learning

Jun 29

Simplified Sparse Attention via Gist Tokens

arXiv:2604. 20920v2 Announce Type: replace Abstract: Sparse attention can reduce the cost of long-context inference, but most variants introduce new architectural components.

By Yuzhen Mao, Michael Y. Li, Emily B. Fox

llms rag efficiency

arXiv Machine Learning

Jun 29

PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding

arXiv:2606. 27440v1 Announce Type: new Abstract: Foundation models for structural biology have achieved remarkable performance in predicting biomolecular structure and show promise for the design of proteins and small molecules.

By Giosue Migliorini, Aristofanis Rontogiannis, Grigori Guitchounts, Nicholas Franklin, Axel Elaldi, Olivia Viessmann

llms rag diffusion safety

arXiv AI

Jun 29

ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

arXiv:2606. 28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks.

By Shijing Hu, Liang Liu, Zhu Meng, Zhicheng Zhao

llms rag agents benchmarks safety

arXiv AI

Jun 29

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation

arXiv:2507. 18632v2 Announce Type: replace-cross Abstract: Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data.

By Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Taewhan Kim, Dong-Jin Kim

rag fine-tuning benchmarks safety

arXiv AI

Jun 29

Distribution-based deep multiple instance learning for tumor proportion scoring in NSCLC

arXiv:2606. 27579v1 Announce Type: cross Abstract: Accurate assessment of tumor proportion score (TPS) in non-small cell lung cancer (NSCLC) is critical for treatment planning and prognosis.

By Krzysztof Pysz, Artur Bartczak, Jaros{\l}aw Kwiecie\'n, Piotr Krajewski, Witold Dyrka

rag

arXiv AI

Jun 29

ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering

arXiv:2606. 27974v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowledge.

By ZhengXian Wu, Hangrui Xu, Kai Shi, Zhuohong Chen, Yunyao Yu, Chuanrui Zhang, Zirui Liao, Jun Yang, Zhenyu Yang, Haonan Lu, Haoqian Wang

rag agents nlp reinforcement-learning fine-tuning multimodal

arXiv AI

Jun 29

Every Step of the Way: Video-based Parkinsonian Turning Step Counting

arXiv:2606. 27918v1 Announce Type: cross Abstract: As a prominent symptom of Parkinson's disease (PD), turning impairment is evaluated through parameters such as turning angle, duration, and particularly, the number of steps required to complete a turn, which directly reflects motor dysfunction.

By Qiushuo Cheng, Jingjing Liu, Catherine Morgan, Alan Whone, Majid Mirmehdi

rag computer-vision

arXiv AI

Jun 29

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

arXiv:2606. 28070v1 Announce Type: new Abstract: JD.

By Oxygen AIIC, Chan Long, Chao Liu, Chaofan Chen, Chaohui Dong, Chunyuan Guo, Danping Liu, Debin Liu, Deping Xiang, Fulai Xu, Guangyue Liu, Hao Li, Huichun Hu, Jian Yang, Jianan Wang, Jianbo Zhao, Jiaoyang Li, Jiaxing Wang, Jinglong Li, Jinjin Guo, Jun Fang, Jun Liu, Kai Zhou, Li Wang, Lili Gao, Liying Chen, Luning Yang, Mengdi Zhou, Pengzhang Liu, Qi Lv, Qianyun Wang, Qixia Jiang, Ruyue Li, Shimu Liang, Shuxing Wang, Sijie Zhang, Siqi Li, Tianhao Gao, Wang Ke, Weihu Huang, Wencan Lai, Wenjie Zhang, Xiaohui Zhang, Xiaojing Dong, Ya Liu, Yifeng Zhang, Yixiang Wang, Yongtai Zhang, Yongyi Liao, Zhaoru Chen, Zhen Chen, Zhiyong Ma, Zhiyuan Liu, Zhongwei Liu, Ziyan Xing

llms rag efficiency multimodal

arXiv AI

Jun 29

HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering

arXiv:2603. 18558v2 Announce Type: replace-cross Abstract: Long-form video question answering requires reasoning over extended temporal contexts, making frame selection a critical bottleneck for multi-modal large language models (MLLMs) bound by finite context windows.

By Dan Ben-Ami, Gabriele Serussi, Kobi Cohen, Chaim Baskin

llms rag computer-vision nlp multimodal benchmarks

arXiv AI

Jun 29

Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting

arXiv:2602. 01588v3 Announce Type: replace-cross Abstract: Multimodal time series forecasting is crucial in real-world applications, where decisions depend on both numerical data and contextual signals.

By Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen, Hung Le

rag multimodal benchmarks safety

arXiv AI

Jun 29

Freshness and the Limits of Heuristic Trend Detection in Temporal RAG

arXiv:2509. 19376v2 Announce Type: replace-cross Abstract: We present a lightweight, model-agnostic temporal layer for RAG and use cybersecurity data to separate two problems that are usually conflated.

By Matthew Grofsky

rag

arXiv AI

Jun 29

On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models

arXiv:2606. 27567v1 Announce Type: cross Abstract: Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken.

By Dewank Pant, Shruti Lohani, Avijit Kumar

llms rag safety

arXiv AI

Jun 29

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

arXiv:2510. 10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs).

By Wentian Zhu, Zhen Xiang, Wei Niu, Le Guan

llms rag nlp robotics fine-tuning benchmarks safety

arXiv Machine Learning

Jun 29

From Detection to Action: Using LLM Agents for Fault-Tolerant Control

arXiv:2606. 28011v1 Announce Type: cross Abstract: We propose an agentic Large Language Model (LLM) framework for active Fault-Tolerant Control (FTC) that transforms fault detection outputs into constraint-aware recovery actions grounded in plant-specific knowledge.

By Javal Vyas, Milapji Singh Gill, Artan Markaj, Felix Gehlhoff, Mehmet Mercang\"oz

llms rag agents benchmarks safety

arXiv Machine Learning

Jun 29

MaRS: Robust Out-of-Distribution Detection via Mahalanobis Residual Scoring

arXiv:2606. 22649v2 Announce Type: replace-cross Abstract: Foundation models provide highly descriptive representations for medical images, yet their reliability degrades under distribution shifts arising from changes in patients, devices, or acquisition conditions.

By Francesco Di Salvo, Sebastian Doerrich, Christian Ledig

rag diffusion

Get the daily briefing