Retrieval-augmented generation

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

6,124 stories · RSS feed

arXiv AI

Oct 15

Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory

arXiv:2610.18238v1 Announce Type: cross Abstract: Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract p...

By Qian Chen, Xianyin Zhang, Lifan Guo, Chi Zhang

llms rag computer-vision multimodal benchmarks

arXiv AI

Oct 15

ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On

arXiv:2610.18325v1 Announce Type: cross Abstract: Virtual footwear try-on (VFTON), a critical yet underexplored area in virtual try-on (VTON), aims to synthesize faithful try-on results given diverse...

By Yuhan Li, Zhiyu Jin, Yifan Tong, Wenxiang Shang, Benlei Cui, Xuanhong Chen, Hangcheng Zhu, Bingbing Ni

rag benchmarks

arXiv AI

Oct 15

ChunkAct: Action Chunking for Agentic Robotics

arXiv:2610.18874v1 Announce Type: cross Abstract: Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-actio...

By Bingxin Xu, Wenrui Bao, Xinxin Liu, Jiawei Zhou, Yuzhang Shang, Emilio Ferrara

llms rag agents robotics multimodal

arXiv AI

Oct 15

Batch Bayesian Active Learning with Partial Batch Label Sampling

arXiv:2510.09877v4 Announce Type: replace-cross Abstract: Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice...

By Kangping Hu, Stephen Mussmann

rag

arXiv AI

Oct 15

GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models

arXiv:2601.07632v5 Announce Type: replace-cross Abstract: Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and m...

By Zhankai Ye, Bofan Li, Yukai Jin, Shuoqiu Li, Wei Wang, Yanfu Zhang, Shangqian Gao, Xin Liu

llms rag nlp fine-tuning efficiency safety

arXiv AI

Oct 15

A Survey of Secure Retrieval-Augmented Generation

arXiv:2604.08304v5 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) improves large language models (LLMs) with external knowledge, but this access path creates security ris...

By Yuming Xu, Mingtao Zhang, Zhuohan Ge, Haoyang Li, Nicole Hu, Yongqi Zhang, Zhiyuan Wen, Jason Chen Zhang, Qing Li, Lei Chen

llms rag agents multimodal

arXiv AI

Oct 15

APEX: Assumption-free Projection-based Embedding eXamination Metric for Generative Distribution Evaluation

arXiv:2605.07786v4 Announce Type: replace-cross Abstract: As generative models achieve unprecedented visual quality, the gold standard for image evaluation remains traditional feature-distribution me...

By Caterina Gallegati, Monica Bianchini, Franco Scarselli, Vittorio Murino, Barbara Toniella Corradini

rag benchmarks safety

arXiv Machine Learning

Oct 15

Lotus: Learning to Understand Time-series by Learning to Forecast

arXiv:2610.18877v1 Announce Type: new Abstract: Time-series language models typically align numerical signals with language using labels, captions, or question-answer pairs. Although such supervision...

By Van Dai Do, Huu Hiep Nguyen, Minh Hoang Nguyen, Manh Nguyen, Hung Le

llms rag

arXiv Machine Learning

Oct 15

Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening

arXiv:2610.18880v1 Announce Type: new Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A d...

By Ziyuan Gao

rag agents efficiency

arXiv Machine Learning

Oct 15

Tracing Morphology, Semantics, and Divergence in Language Acquisition

arXiv:2610.19041v1 Announce Type: new Abstract: Understanding the dynamics of language acquisition in Large Language Models (LLMs) is crucial for uncovering how statistical representations evolve int...

By Forough Shirin Abkenar, Haoshuo Fu, Liang Feng, Ning Yan, Masood S. Mortazavi

llms rag

arXiv Machine Learning

Oct 15

Exact Scaling Laws for a Random-Features Bigram Model

arXiv:2610.19281v1 Announce Type: new Abstract: Understanding neural scaling laws is increasingly important for theory and practice, yet first-principles explanations remain limited even in simple se...

By Julian Enoch, Elvis Dohmatob

llms rag

arXiv Machine Learning

Oct 15

Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context

arXiv:2610.19364v1 Announce Type: new Abstract: Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do...

By Bo Li, Yue Yang, Yujin Huang, Siao Liu, David Lemphers, Sara E Rodriguez Gomez, Luke Borgnolo, Can Wang, Xin Zheng

rag

arXiv Machine Learning

Oct 15

W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition

arXiv:2610.19411v1 Announce Type: new Abstract: A major challenge in wearable device activity recognition is the heterogeneity across datasets in sensor placement, channel count, sampling rate and su...

By Yogesh Prabhu, Loki Natarajan, Jingjing Zou

rag nlp benchmarks

arXiv Machine Learning

Oct 15

Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap

arXiv:2610.19065v1 Announce Type: cross Abstract: Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers...

By Renbo Tu, Yang Liu, Shuying Sun

llms rag

arXiv Machine Learning

Oct 15

Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification

arXiv:2601.16834v4 Announce Type: replace Abstract: Wall-to-wall biomass density estimation from NASA's GEDI mission requires interpolating sparse LIDAR observations across heterogeneous landscapes....

By Robin Young, Srinivasan Keshav

rag

arXiv Machine Learning

Oct 15

TabFORGE: A Tabular Foundation Model for Generative Modelling

arXiv:2605.09424v2 Announce Type: replace Abstract: Generative modelling is a demanding test of foundation models, because it requires robust, holistic representation learning for a given data modali...

By Xiangjian Jiang, Mingxuan Liu, Nikola Simidjievski, Tassilo Klein, Mateja Jamnik

llms rag diffusion benchmarks safety data-engineering

arXiv Machine Learning

Oct 15

Deep kernel hedging

arXiv:2609.34474v2 Announce Type: replace Abstract: We introduce a deep kernel hedging framework that combines the flexibility of deep learning with the structural inductive bias of kernel methods. T...

By Jean-Loup Dupret, Donatien Hainaut, Edouard Motte

rag safety

arXiv Computation and Language

Oct 15

Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts

arXiv:2610.20067v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently encounter conflicts between internal parametric knowledge and external contextual knowledge, yet the mechanisms...

By Yibin Lou, Yi Hu, Jianhui Chen, Chenpeng Wang, Muhan Zhang, Liangming Pan

llms rag

arXiv Computation and Language

Oct 15

When Occupation-derived Skills Don't Help: On the Limits of Skill-Augmented Career Path Prediction

arXiv:2610.20186v1 Announce Type: new Abstract: Skills are widely assumed to play a central role in career transitions, motivating their use in career path prediction (CPP) systems. In this work, we...

By Ege S\"ualp, Elena Senger, Toine Bogers, Barbara Plank

rag benchmarks

arXiv Computation and Language

Oct 15

$\pi$-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering

arXiv:2506.20642v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with comple...

By Chao Wan, Albert Gong, Mihir Mishra, Carl-Leander Henneking, Claas Beger, Kilian Q. Weinberger

llms rag benchmarks

Get the daily briefing