Retrieval-augmented generation

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

6,375 stories · RSS feed

arXiv AI

Sep 15

RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes

arXiv:2609.14100v1 Announce Type: cross Abstract: Fashion Image Captioning (FIC) plays a vital role in enhancing user experience and product search in e-commerce platforms. Unlike natural scene image...

By Abhirama Subramanyam Penamakuri, Shreya Shukla, Anand Mishra

llms rag fine-tuning multimodal

arXiv Machine Learning

Sep 15

PPDL: A Real-world Industrial User Retention Ratio Forecasting Framework Integrating Physical Priors with Deep Learning

arXiv:2609.13789v1 Announce Type: new Abstract: In multi-channel paid user acquisition, early and accurate prediction of user retention at the channel level is crucial for optimizing budget allocatio...

By Zibo Zhao, Zhengxiong Guan, Chaoli Zhang, Linyuan Geng, Xuanbing Zhu, Zhonglong Zheng, Fan Wu

rag

arXiv Computer Vision

Sep 15

Accurate and Scalable Multimodal Pathology Retrieval via Attentive Vision-Language Alignment

arXiv:2510.23224v2 Announce Type: replace Abstract: The rapid digitization of histopathology slides has opened new opportunities for computational tools in clinical and research workflows. Content-ba...

By Hongyi Wang, Zhengjie Zhu, Junlin Hou, Jiabo Ma, Fang Wang, Yue Shi, Qiuyu Cai, Jili Wang, Bo Luo, Zhizhong Chai, Zhengyu Zhang, Li Liang, Xiuming Zhang, Yen-Wei Chen, Lanfen Lin, Hao Chen

rag multimodal safety

arXiv AI

Sep 15

Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help

arXiv:2609.13718v1 Announce Type: cross Abstract: AI-powered gameplay support agents hold promise for game-based learning, yet grounding generative models in structured game data remains an open chal...

By Jiahong Li, Sai Siddartha Maram, Atieh Kashani, Ulia Zaman, Zhiyu Lin, Cameron Marano, Roger Azevedo, Jichen Zhu, Magy Seif El-Nasr

llms rag agents

arXiv Computer Vision

Sep 15

Human Pose-Constrained UV Map Estimation

arXiv:2501.08815v2 Announce Type: replace Abstract: UV map estimation is used in computer vision for detailed analysis of human posture or activity. Previous methods assign pixels to body model verti...

By Matej Suchanek, Miroslav Purkrabek, Jiri Matas

rag computer-vision

arXiv Machine Learning

Sep 15

Multimodal deep learning from spectra for small-molecule structure identification: enhancing robustness with mixed-condition training

arXiv:2609.14360v1 Announce Type: new Abstract: In practical molecular characterization, small-molecule structure identification benefits from complementary spectroscopic evidence, but missing, degra...

By Bowen Gao, Lei Zhu, Yiying Wang, Wenjie Yu

rag multimodal

arXiv Computation and Language

Sep 15

To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs

The paper proposes a modular tokenizer framework for multilingual large language models, allowing the creation of language‑specific subtokenizers that match monolingual compression quality. It introduces a pretraining strategy that samples these subtokenizers to limit predictions to relevant vocabularies, enabling efficient training and inference. This approach reduces memory usage and speeds up inference without compromising performance.

By Franck Signe, Hippolyte Pilchen, Fran\c{c}ois Yvon, \'Edouard Grave

llms rag nlp safety

arXiv AI

Sep 15

Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation

Fraglingo is an autoregressive fragment-based molecular generator that jointly models fragment identity and attachment in a continuous latent space. It predicts attachment-aware fragment embeddings using a wildcard-anchored readout that captures the growing molecule’s active attachment site, then retrieves the next fragment via latent-space nearest-neighbor search. This approach allows new fragments to be added at inference time without retraining and achieves stronger joint property control on benchmarks while maintaining high validity, uniqueness, and novelty.

By Thao Nguyen, Jeonghwan Kim, Zhenhailong Wang, Heng Ji

rag diffusion benchmarks

arXiv AI

Sep 15

Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores

arXiv:2601.13885v2 Announce Type: replace-cross Abstract: Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluatio...

By Esma Balk{\i}r, Alice Pernthaller, Marco Basaldella, Jos\'e Hern\'andez-Orallo, Nigel Collier

llms rag benchmarks

arXiv Computer Vision

Sep 15

AlignUS: MRI-Guided Ultrasound Representation Learning for ALS Classification from Tongue Images

arXiv:2609.15285v1 Announce Type: new Abstract: Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease in which early assessment remains challenging, particularly in low-resou...

By Kadija Abdel Ghader, Emani Babe, Lorenzo Pettinari, Meya Haroune, Sidaty El Hadramy

rag efficiency multimodal

arXiv Computer Vision

Sep 15

Weakly Supervised Spatial Grounding for Discriminative Attention-Based Ultrasound-Histopathology Alignment in Prostate Cancer Grading

arXiv:2609.15150v1 Announce Type: new Abstract: Unpaired cross-modal distillation transfers grade structure from histopathology into a micro-ultrasound (micro-US) encoder by aligning a pooled needle-...

By Obed Korshie Dzikunu, Emma Willis, Mohammad Mahdi Abootorabi, Mohamed Harmanani, Zhuoxin Guo, Ferdinand Luger, Adam Kinnaird, Brian Wodlinger, Parvin Mousavi, Purang Abolmaesumi

rag efficiency multimodal benchmarks safety

arXiv AI

Sep 15

Attention Calibration for Position-Fair Dense Retrieval

arXiv:2606.02737v2 Announce Type: replace-cross Abstract: Dense retrieval compresses a passage into a single vector, but this compression is positionally skewed: early content dominates the embedding...

By Andrianos Michail, Elias Schuhmacher, Juri Opitz, Simon Clematide, Rico Sennrich

llms rag benchmarks

arXiv AI

Sep 15

Predictive audio representations for early detection and tracking of hidden dynamic objects

arXiv:2609.13595v1 Announce Type: cross Abstract: Predicting potential dangers is core to safety. Forecasting the presence of other traffic agents is core to danger prediction. Occluded traffic agent...

By Katerina Vinciguerra, Moritz Brandes, Danilo Hollosi, Letizia Marchegiani

rag agents fine-tuning safety

arXiv Computation and Language

Sep 15

Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights

arXiv:2609.08797v2 Announce Type: replace-cross Abstract: The Potts model extends the Ising model to multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pa...

By Matthias von Davier

llms rag efficiency

arXiv Computation and Language

Sep 15

A Ticket from Marginals to Joints: Coupled-Noise Distillation for One-Step Block Generation in Diffusion Language Models

arXiv:2609.06324v2 Announce Type: replace Abstract: Diffusion language models (dLLMs) predict all tokens of a block in parallel, but a single forward pass samples each position from its own marginal...

By Lin Yao

llms rag diffusion efficiency

arXiv AI

Sep 15

TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control

arXiv:2601.14945v3 Announce Type: replace-cross Abstract: Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency because they adopt a low...

By Yuteng Sun, Haoran Wang, Ruofei Bai, Zhengguo Li, Jun Li, Meng Yee Michael Chuah, Wei Yun Yau

rag diffusion robotics efficiency multimodal

arXiv AI

Sep 15

How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms

arXiv:2606.09646v2 Announce Type: replace-cross Abstract: We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this inform...

By Samuele Punzo, Niccol\`o Caselli, Ippokratis Pantelidis, Francesco Massafra, Salvatore Lo Sardo, Mohammadreza Salehi

rag diffusion benchmarks

arXiv AI

Sep 15

The Attribution-Compression Frontier in Retrieval-Augmented Generation

arXiv:2609.14245v1 Announce Type: cross Abstract: Context compression reduces generator input in retrieval-augmented generation, but answer quality alone does not characterize citation attribution. W...

By Deepanshu Mody

rag nlp efficiency

arXiv AI

Sep 15

Biquaternionic Space with Complex-valued Attention for Temporal Knowledge Graph Completion

arXiv:2609.14279v1 Announce Type: cross Abstract: Temporal knowledge graph embedding (TKGE) models infer missing facts in knowledge graphs that evolve over time. Many existing models use a single geo...

By Rushan Geng, Cuicui Luo

rag benchmarks

arXiv Machine Learning

Sep 15

Retrieval-Guided Fine-Tuning as Noisy Estimation: Risk bounds and Architectural Analysis

arXiv:2609.14485v1 Announce Type: new Abstract: Retrieval-Guided Fine-Tuning (RAG-FT) incorporates retrieved data directly into the training objective, but the statistical consequences of noisy retri...

By Bhargav Lad, Yifan Hao

rag fine-tuning safety

Get the daily briefing