Retrieval-augmented generation

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

6,427 stories · RSS feed

arXiv Machine Learning

Aug 6

Attention-Only White-Box Transformer via LeJEPA-Based Self-Supervised Pretraining

arXiv:2608. 04213v1 Announce Type: new Abstract: Existing studies on self-supervised learning for white-box networks typically decouple the derivation of white-box networks via optimization algorithms from self-supervised learning paradigms.

By Yang Bai, Linyuan Wang, Haoyang Jiang, Nuolin Sun, Libin Hou, Bin Yan

llms rag efficiency

arXiv AI

Aug 6

SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors

arXiv:2608. 04060v1 Announce Type: cross Abstract: Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural maps.

By Yongchao Huang

rag

arXiv AI

Aug 6

RAG-Stack: Co-Optimizing RAG Serving Performance and Quality

arXiv:2608. 03487v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a widely used approach for knowledge-intensive applications.

By Haiqiang Zhang, Yuanqing Lei, Wanting Li, Tao Zhang, Wenqi Jiang

llms rag benchmarks

arXiv Machine Learning

Aug 6

A Mechanistic Analysis of Transformers for Dynamical Systems

arXiv:2512. 21113v2 Announce Type: replace Abstract: Transformers are increasingly adopted for modeling and forecasting time-series, yet their internal mechanisms remain poorly understood from a dynamical systems perspective.

By Gregory Duth\'e, Nikolaos Evangelou, Wei Liu, Ioannis G. Kevrekidis, Eleni Chatzi

llms rag

arXiv Machine Learning

Aug 6

Kathleen Writes: Autoregressive Generation and Data Scaling Without Attention

arXiv:2608. 04678v1 Announce Type: cross Abstract: Papers 1-2 of the Kathleen series showed that a byte-level, attention-free architecture built from a wavetable encoder and multi-scale reverberant state can match strong baselines on classification at ~450-700K parameters, without pretraining.

By George Fountzoulas

llms rag nlp benchmarks

arXiv Machine Learning

Aug 6

DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models

arXiv:2608. 04477v1 Announce Type: cross Abstract: Cloud-based language model services routinely process prompts containing sensitive information.

By Zhicong Huang, Cheng Hong, Tao Wei

llms rag

arXiv Machine Learning

Aug 6

Above-ground Biomass Estimation with Geospatial Foundation Models

arXiv:2608. 04792v1 Announce Type: new Abstract: Accurate estimation of Above-Ground Biomass (AGB) from satellite imagery is essential for the large-scale monitoring of carbon stocks, yet it remains a challenging regression task at global scale.

By Ghjulia Sialellia, Linus Scheibenreif, Jan Dirk Wegner, Konrad Schindler

rag computer-vision benchmarks

arXiv AI

Aug 6

From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking

arXiv:2608. 05030v1 Announce Type: new Abstract: Football score forecasting combines a strong statistical core with a difficult contextual edge.

By Shaopeng Liang

llms rag benchmarks

arXiv AI

Aug 6

MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation

arXiv:2608. 05076v1 Announce Type: cross Abstract: Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam prediction, and localization based on wireless signals.

By Blessed Guda, Kayley Sze, Carlee Joe-Wong

llms rag fine-tuning benchmarks

arXiv Machine Learning

Aug 6

DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery

arXiv:2608. 05120v1 Announce Type: new Abstract: Kinetic model discovery is a central challenge in chemical engineering, as accurate rate expressions are essential for understanding and controlling chemical and biological processes.

By Roberto Aliaga Medina, Paulina Quintanilla, Antonio del Rio Chanona

llms rag benchmarks

arXiv Machine Learning

Aug 6

Attention-based representations for multi-task computation

arXiv:2608. 04243v1 Announce Type: new Abstract: Multi-head attention layers produce vector representations that support multiple downstream tasks.

By Daniel Hsu, Mingyue Xu

rag

arXiv AI

Aug 6

Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning

arXiv:2608. 04457v1 Announce Type: cross Abstract: As "AI Scientists" emerge to drive research via the Model Context Protocol (MCP), systems relying on ephemeral scripts will fail.

By Hans-Martin Will, Allen L. Brown Jr., Matthew Fuchs

rag agents

arXiv AI

Aug 6

Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation

arXiv:2608. 04170v1 Announce Type: cross Abstract: AI co-scientists can generate fluent materials-science hypotheses, but fluency does not show that an answer preserves a scientifically meaningful mechanism.

By Shashwat Sourav, Subhadeep Pal, Markus J. Buehler, Sanjay Das, Fiona Y. Wang, Dominik Soos, Tirthankar Ghosal

llms rag

arXiv Machine Learning

Aug 6

BIM-Native Tokenization for Constraint-Aware Room Layout Synthesis

arXiv:2512. 04832v3 Announce Type: replace-cross Abstract: We present a BIM-native tokenization for room-level layout synthesis in Building Information Modeling (BIM) scenes.

By Manuel Ladron de Guevara, Jinmo Rhee, Ardavan Bidgoli, Vaidas Razgaitis, Michael Bergin

llms rag nlp benchmarks

arXiv Machine Learning

Aug 6

Predicting Brain Morphometry with MT-GNN: Mesh Evolution in Continuous Time with Graph-Based Metric Tensor Embeddings

arXiv:2608. 05132v1 Announce Type: cross Abstract: Predicting how a subcortical structure's shape will evolve from a few prior scans could support prognosis and clinical-trial enrichment.

By Hao Ding, Daniel Semchin, Paul M. Thompson, Boris Gutman

llms rag

arXiv Machine Learning

Aug 6

Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation

arXiv:2608. 04378v1 Announce Type: cross Abstract: Collaborative music agents need internal representations rich enough to support both understanding and generation, yet flexible enough for a workflow where the human retains agency.

By Scott H. Hawley

llms rag agents

arXiv Machine Learning

Aug 6

Right Reset: Chunking by Prefix Removal

arXiv:2608. 04330v1 Announce Type: cross Abstract: Removing the left context from a causal language model reveals a useful kind of boundary: an edge where the model processes the same right-hand tokens with little change.

By Mike Vegeto

llms rag computer-vision

arXiv Machine Learning

Aug 6

Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression

arXiv:2608. 04569v1 Announce Type: cross Abstract: Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget.

By Zhengpei Hu, Kai Li, Dapeng Fu, Xuechao Zou, Yuanhao Tang, Yue Li, Tengfei Cao, Jianqiang Huang

llms rag nlp

arXiv AI

Aug 6

Tropical Algebraic Geometry for Neuronal Representations: An Arakelov-Green Measure Based Descriptor for Graph Learning

arXiv:2608. 04460v1 Announce Type: cross Abstract: The quantitative analysis of 3D neuronal morphologies requires capturing both graph topology and spatial geometry.

By Yuyang Zhang, Weihan Xu, Xuehai Zhou, Shucheng Cao, Qihuang Zhang

rag efficiency benchmarks

arXiv AI

Aug 6

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents

arXiv:2608. 02009v2 Announce Type: replace Abstract: Retrieval-augmented search agents answer multi-hop questions by repeatedly issuing search queries and accumulating evidence.

By Daeyoung Roh, Donghee Han

rag agents benchmarks safety

Get the daily briefing