Retrieval-augmented generation

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

6,126 stories · RSS feed

arXiv Machine Learning

Oct 8

It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank

arXiv:2610.09517v1 Announce Type: cross Abstract: Frozen vision-language models increasingly provide safety signals for reinforcement learning. Their use assumes that similarity to language describin...

By Samuel Tetteh, Cody Fleming

llms rag reinforcement-learning multimodal benchmarks safety

arXiv Computation and Language

Oct 8

A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks

arXiv:2610.09835v1 Announce Type: new Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using o...

By Jonghyun Han, Younghoon Song, Jongyoul Park

llms rag fine-tuning

arXiv Computation and Language

Oct 8

Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression

arXiv:2610.09788v1 Announce Type: new Abstract: Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can in...

By Mingqing Yuan (Soochow University), Xiaobo Liang (Soochow University), Junwei Yang (University of Cambridge), Ziwei Chen (Chalmers University of Technology), Zeren Zhang (Peking University), Hejin Wang (Tsinghua University), Yubin Wang (The Hong Kong University of Science,Technology), Juntao Li (Soochow University)

rag agents diffusion reinforcement-learning fine-tuning benchmarks

arXiv Computation and Language

Oct 8

PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency

arXiv:2610.09761v1 Announce Type: cross Abstract: Text-to-point-cloud localization estimates a position in a city-scale 3D map from descriptions of surrounding objects. Existing coarse-to-fine method...

By Shengkai Ma, Zhenyu Hou, Weihua Cao

rag multimodal

arXiv Computer Vision

Oct 8

STORK: Spatio-Temporal Observation of uterine contRactions via neural networKs

arXiv:2610.09598v1 Announce Type: new Abstract: Uterine contractions in fetal MRI are typically identified manually and discarded, limiting insights into contraction dynamics. We formalize Uterine Co...

By Melissa Schween, Tristan Gottwald, Jordina Aviles Verdera, Lisa Story, Mary Rutherford, Jana Hutter

rag

arXiv Machine Learning

Oct 8

Towards AI-Generated Music Plagiarism Detection as a Version Identification Problem

The paper addresses the challenge of detecting plagiarism in music generated by AI, noting that traditional binary notions of plagiarism are insufficient due to nuanced musical elements. It evaluates whether existing music version identification models, originally designed for human covers, can transfer to human-to-AI plagiarism detection. The authors introduce COPYCAT, a large benchmark of 350,654 pairs derived from real plagiarism cases and augmented with generative re‑synthesis and DSP obfuscations, and demonstrate that a supervised embedding‑shift approach significantly improves detection performance over simple distance thresholding.

By Fotis Koutsikos, Ioannis Prokopiou, Spyridon Kantarelis, Vassilis Lyberatos, Pantelis Vikatos, Athanasios Aidinis, Themos Stafylakis, Athanasios Voulodimos, Giorgos Stamou

rag benchmarks

arXiv Machine Learning

Oct 8

A Strength-Monotonic Law for Domain Alignment in Frozen-Embedding Bioacoustic Classification

arXiv:2610.09737v1 Announce Type: cross Abstract: When does distribution alignment help a frozen foundation-model embedding generalize across acoustic domains? For cross-domain mosquito-species class...

By Yucheng Gong, Rui Zhou, Binbin Zeng, Qiang Ren, Hongjin Hui

rag fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Oct 8

Graph-Based Floor Separation Using Node Embeddings and Clustering of WiFi Trajectories

arXiv:2505.08088v5 Announce Type: replace-cross Abstract: Indoor positioning systems (IPSs) are increasingly vital for location-based services in complex multi-storey environments. This study propose...

By Rabia Yasa Kostas, Kahraman Kostas

rag

arXiv Machine Learning

Oct 8

Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting

arXiv:2603.11938v2 Announce Type: replace-cross Abstract: Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must...

By Chantal Pellegrini, Adrian Delchev, Ege \"Ozsoy, Nassir Navab, Matthias Keicher

llms rag multimodal benchmarks

arXiv Computation and Language

Oct 8

QuanLing: Cross-Branch Validation of Language Distance Quantification on Western Romance

arXiv:2610.08851v1 Announce Type: new Abstract: Quantifying language distance among closely related languages remains a core challenge in quantitative linguistics. Our previous work [1] introduced Qu...

By Yiping Bai

llms rag nlp

arXiv Computer Vision

Oct 8

SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code

arXiv:2610.09116v1 Announce Type: new Abstract: The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them. We introduce SPLATI...

By Seemandhar Jain, Keshav Gupta, Manmohan Chandraker

rag agents multimodal

arXiv Computer Vision

Oct 8

Masked Feature Encoding for Large-Scale Whole Slide Image Representation

arXiv:2610.10225v1 Announce Type: new Abstract: Whole slide image (WSI) analysis in computational pathology follows a multiple instance learning (MIL) pipeline where patch embeddings are extracted in...

By Haoyu He, Basile Tessier-Cloutier, Yang Wang, Mahdi S. Hosseini

rag computer-vision

arXiv Computer Vision

Oct 8

Detecting Adversarial Images through Response Profiles of Vision-Language Models

arXiv:2610.10436v1 Announce Type: new Abstract: Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity p...

By Arash Vashagh, Roozbeh Razavi-Far

llms rag multimodal safety

arXiv Machine Learning

Oct 8

Self-attention summary networks for subsurface velocity-model building from common-image gathers

arXiv:2610.09282v1 Announce Type: new Abstract: Common-image gathers (CIGs) contain physically meaningful information about velocity-model errors through reflector focusing and residual moveout, but...

By Shiqin Zeng, Yunlin Zeng, Abhinav Prakash Gahlot, Zijun Deng, Felix J. Herrmann

rag

arXiv Machine Learning

Oct 8

KVFetch: Temporal Prefetching for the Missing Half of KV Cache Compression

arXiv:2610.08811v1 Announce Type: new Abstract: As context windows scale to tens or hundreds of thousands of tokens, KV cache compression has become essential for efficient LLM inference. Existing me...

By Linfeng Dong

llms rag efficiency

arXiv Machine Learning

Oct 8

Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers

arXiv:2610.09003v1 Announce Type: new Abstract: Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and...

By Sourabh Kasliwal

llms rag benchmarks

arXiv Machine Learning

Oct 8

Dataset Pruning from First Principles: A Label-Free Linear Programming Approach

arXiv:2610.10347v1 Announce Type: cross Abstract: Dataset pruning reduces a large training set to a representative subset while preserving model performance. Existing geometry-based methods typically...

By Rodrigo Schuller, Francisco Ganacim

rag efficiency benchmarks

arXiv Machine Learning

Oct 8

Control-Geometry Straightening for Sampling-Based Latent Planning

arXiv:2609.35603v2 Announce Type: replace Abstract: Joint-embedding predictive architectures enable planning with latent world models, but accurate transition prediction alone does not ensure that th...

By Ziang Fu, Ning Ning

rag

arXiv Machine Learning

Oct 8

TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning

arXiv:2605.07943v2 Announce Type: replace-cross Abstract: Active vision -- where a policy controls its own gaze during manipulation -- has emerged as a key capability for imitation learning, with mul...

By Giacomo Spigler

rag diffusion robotics benchmarks

arXiv Machine Learning

Oct 8

An Empirical Study of Agent Skills' Downstream Utility

arXiv:2610.08875v1 Announce Type: cross Abstract: Agent Skills package procedural guidance and resources for reuse, but a relevant Skill does not necessarily improve task performance. Existing studie...

By Yu Cheng, Dehai Zhao, Zhongxin Liu, Qing Huang, Zhenchang Xing, Xiaoxue Ren

llms rag agents

Get the daily briefing