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 AI

Jun 16

Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time

arXiv:2606. 15631v1 Announce Type: cross Abstract: Extending a vision-language-action (VLA) policy to a new task typically requires task-specific teleoperated demonstrations and per-task fine-tuning, making adaptation costly in both data collection and compute.

By Jeongeun Park, Juhan Park, Taekyung Kim, Sungjoon Choi, Dongyoon Han, Sangdoo Yun

rag robotics fine-tuning multimodal

arXiv AI

Jun 16

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

arXiv:2606. 16497v1 Announce Type: cross Abstract: GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective.

By Dayuan Fu, Mohan Jiang, Tongyu Wang, Dian Yang, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Li

llms rag agents nlp reinforcement-learning fine-tuning

arXiv AI

Jun 16

RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking

arXiv:2604. 20623v2 Announce Type: replace-cross Abstract: Traditional change detection identifies where changes occur, but does not explain what changed in natural language.

By Roie Kazoom, Yotam Gigi, George Leifman, Tomer Shekel, Genady Beryozkin

rag computer-vision multimodal benchmarks

arXiv AI

Jun 16

Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations

arXiv:2606. 14817v1 Announce Type: cross Abstract: This work presents the design, implementation, and evaluation of a system for generating personalized reading content using Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG).

By Sooyeon Kim, Piotr S. Maci\k{a}g

llms rag safety

arXiv AI

Jun 16

Akasha 2: Hamiltonian State Space Duality and Visual-Language Joint Embedding Predictive Architectur

arXiv:2601. 06212v2 Announce Type: replace-cross Abstract: We present Akasha 2, a state-of-the-art multimodal architecture that integrates Hamiltonian State Space Duality (H-SSD) with Visual-Language Joint Embedding Predictive Architecture (VL-JEPA).

By Yani Meziani

llms rag diffusion multimodal benchmarks

arXiv Machine Learning

Jun 16

Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting

arXiv:2603. 14709v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enhances zero-shot time series (TS) forecasting by leveraging external knowledge bases, yet existing approaches overlook input-level relevance when fusing retrieved samples with the query.

By Seunghan Lee, Jaehoon Lee, Jun Seo, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, SoonYoung Lee, Wonbin Ahn

rag

arXiv AI

Jun 16

Guiding Federated Graph Recommendation with LLM-encoded knowledge

arXiv:2606. 15277v1 Announce Type: cross Abstract: Graph-based recommender systems are highly effective at extracting collaborative signals from user--item interactions, and federated learning (FL) allows these models to be trained while preserving user privacy.

By Thi Minh Chau Nguyen, Hien Trang Nguyen, Duc Anh Nguyen, Van Ho-Long, Thanh Trung Huynh, Zhao Ren

llms rag benchmarks safety

arXiv AI

Jun 16

ArtNet: A JEPA-Like Articulatory Predictive Framework for Robust Zero-Shot Phoneme Recognition

arXiv:2606. 16595v1 Announce Type: cross Abstract: Zero-shot cross-lingual phoneme recognition is often hindered by the fragility of direct acoustic-to-symbol mapping, which is susceptible to language-specific variations.

By Zeqian Hu, Fuliang Weng, Shu Shang, Yaqian Zhou

rag safety

arXiv AI

Jun 16

Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations

arXiv:2606. 15335v1 Announce Type: cross Abstract: When distributed agents exchange text across organizational boundaries, privacy leakage arises not only from explicit identifiers but also from distributional signatures such as formatting conventions, vocabulary choices, and syntactic patterns.

By Xuan Liu, Hefeng Zhou, Sicheng Chen, Chao Yang, Xingcheng Xu, Jingjing Qu, Jiong Lou, Jie LI, Xia Hu

rag agents benchmarks safety

arXiv AI

Jun 16

Near--Real-Time Conflict-Related Fire Detection in Sudan Using Unsupervised Deep Learning

arXiv:2512. 07925v4 Announce Type: replace-cross Abstract: Ongoing armed conflict in Sudan highlights the need for rapid monitoring of conflict-related fire-affected areas.

By Kuldip Singh Atwal, Dieter Pfoser, Daniel Rothbart

rag

arXiv AI

Jun 16

Discrete optimal transport is a strong audio adversarial attack

arXiv:2509. 14959v3 Announce Type: replace-cross Abstract: In this paper, we investigate discrete optimal transport (DOT) as a black-box attack against modern automatic speaker verification (ASV) and anti-spoofing countermeasure (CM) systems.

By Anton Selitskiy, Akib Shahriyar, Jishnuraj Prakasan

rag fine-tuning safety

arXiv Machine Learning

Jun 16

Active Learning with Low-Rank Structure for Data Selection

arXiv:2606. 16045v1 Announce Type: new Abstract: In the data selection problem, the objective is to choose a small, representative subset of data that can be used to efficiently train a machine learning model.

By Vincent Cohen-Addad, Sasidhar Kunapuli, Vahab Mirrokni, Mahdi Nikdan, David P. Woodruff, Samson Zhou

rag

arXiv AI

Jun 16

Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting

arXiv:2606. 16076v1 Announce Type: cross Abstract: Multivariate forecasting in physical systems requires models that predict coupled temporal variables while preserving meaningful state evolution.

By Weizhi Nie, Weichao Liu, Honglin Guo, Yuting Su

rag

arXiv Machine Learning

Jun 16

PHINN: Persistent Homology Inspired Neural Network for Rare-Event Time Series Generation

arXiv:2606. 15452v1 Announce Type: new Abstract: Rare events in time series are critical to model but hard to learn due to data scarcity.

By Emre Yusuf, Ren Takahashi, Jayabrata Bhaduri

rag diffusion multimodal benchmarks safety

arXiv AI

Jun 16

G-Loss: Graph-Guided Fine-Tuning of Language Models

arXiv:2604. 25853v3 Announce Type: replace-cross Abstract: Traditional loss functions, including cross-entropy, contrastive, triplet, and su pervised contrastive losses, used for fine-tuning pre-trained language models such as BERT, operate only within local neighborhoods and fail to account for the global semantic structure.

By Aditya Sharma, Vinti Agarwal, Rajesh Kumar

llms rag nlp fine-tuning benchmarks

arXiv AI

Jun 16

Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing

arXiv:2603. 17531v2 Announce Type: replace-cross Abstract: Recent advancements in diffusion-based image editing pose a significant threat to the authenticity of digital visual content.

By Pengzhen Chen, Yanwei Liu, Xiaoyan Gu, Xiaojun Chen, Wu Liu, Weiping Wang

rag diffusion

arXiv Machine Learning

Jun 16

Discriminative Span as a Predictor of Synthetic Data Utility via Classifier Reconstruction

arXiv:2605. 09697v3 Announce Type: replace-cross Abstract: In many real-world computer vision applications, including medical imaging and industrial inspection, binary classification tasks are characterized by a severe scarcity of positive samples.

By Radhika Amar Desai, Modigari Narendra

rag computer-vision data-engineering

arXiv AI

Jun 16

E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory

arXiv:2601. 21714v5 Announce Type: replace Abstract: The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons.

By Kaixiang Wang, Yidan Lin, Jiong Lou, Zhaojiacheng Zhou, Bunyod Suvonov, Jie Li

llms rag agents benchmarks

arXiv AI

Jun 16

An Empirical Study on Learning Latent Representations for Emotional Speech Synthesis

arXiv:2606. 14922v1 Announce Type: cross Abstract: For the last couple of years, the field of speech synthesis has improved dramatically thanks to deep learning.

By Vinh Dang Quang, Huy Ngo Quang

rag

arXiv Machine Learning

Jun 16

Semi-Supervised Speech Confidence Detection using Pseudo-Labelling and Whisper Embeddings

arXiv:2606. 16505v1 Announce Type: cross Abstract: Understanding speaker confidence is crucial in educational settings, as it can enhance personalised feedback and improve learning outcomes.

By Adam Wynn, Jingyun Wang, Xiangyu Tan

rag multimodal

Get the daily briefing