Retrieval-augmented generation

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

3,089 stories · RSS feed

arXiv AI

Jul 14

When Sensing Varies with Contexts: Context Probing for Tactile Few-Shot Class-Incremental Learning

arXiv:2603. 25115v2 Announce Type: replace Abstract: Few-shot class-incremental learning (FSCIL) aims to recognize novel classes from only a few labeled samples while retaining previously learned knowledge.

By Yifeng Lin, Aiping Huang, Wenxi Liu, Si Wu, Tiesong Zhao, Zechao Li, Zheng-Jun Zha

rag benchmarks

arXiv Machine Learning

Jul 14

Learning Subgroup Relations Using Siamese Graph Neural Networks

arXiv:2607. 11140v1 Announce Type: new Abstract: Determining whether one finite group is isomorphic to a subgroup of another is a fundamental problem in computational group theory.

By Tal Weissblat

rag

arXiv Machine Learning

Jul 14

Observable Performance Does Not Fully Reflect Adaptive System Organization: A Multi-Level Analysis of Gait Dynamics Under Occlusal Constraint

arXiv:2605. 00778v2 Announce Type: replace Abstract: In biomechanical systems, observable performance is often used as a proxy for underlying organization, although similar outputs may arise from different adaptive configurations.

By Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit

rag

arXiv Machine Learning

Jul 14

From Performance to Representational Adequacy: A Representational Bootstrap Framework for Adaptive Biological Systems

arXiv:2606. 01374v3 Announce Type: replace Abstract: Observable performance is commonly used to characterize biological systems, yet aggregated outputs may remain insufficient for uniquely resolving observational conditions, and richer multivariate representations may retain substantial ambiguity.

By Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit

rag

arXiv AI

Jul 14

Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks

arXiv:2607. 09739v1 Announce Type: new Abstract: We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the full benchmark suite.

By Jihan Yao, Gantavya Bhatt, Arnav Das, Peter Jin, Ke Bao, Qiaolin Yu, Khushi Bhardwaj, Chang Su, Jialei Wang, Yikai Zhu, Sugam Devare, Damon Mosk-Aoyama, Zhen Dong, Venkat Krishna Srinivasan, Yineng Zhang, Oleksii Kuchaiev, Jiantao Jiao, Banghua Zhu, Jeff Bilmes

llms rag benchmarks

arXiv AI

Jul 14

PhenoEmbed: Self-Supervised Multispectral UAV Time-Series Embeddings for Individual Tree Crown Phenology

arXiv:2607. 10231v1 Announce Type: cross Abstract: Tree crowns are a challenging target for resilient AI because they are not static objects: their spectral response, internal texture, translucency, and apparent boundaries change substantially across the growing season.

By Taimur Khan

rag benchmarks

arXiv AI

Jul 14

Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories

arXiv:2607. 11725v1 Announce Type: cross Abstract: Prefabricated prefinished volumetric construction moves most building work into module factories, whose production floor operates as a flexible job shop.

By Ziheng Zhang, Wei Zhang

rag reinforcement-learning benchmarks

arXiv Machine Learning

Jul 14

EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning

arXiv:2607. 10491v1 Announce Type: new Abstract: Retrieval-augmented generation grounds large language models in external evidence, but most pipelines still treat retrieved passages as deterministic and mutually consistent context.

By S M Asif Hossain, Ruksat Khan Shayoni, M. F. Mridha

llms rag nlp safety

arXiv AI

Jul 14

GAE: Graph-Augmented Evolution for Scientific Discovery via Reinforcement Optimization

arXiv:2607. 10127v1 Announce Type: cross Abstract: Evolutionary program search guided by Large Language Models (LLMs) has emerged as a powerful paradigm for automated scientific discovery.

By Xuanzhou Chen, Taoli Cheng

llms rag reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 14

Towards Objective Dysgraphia Detection: A Multi-Branch Deep Learning Approach for Online Handwriting Analysis

arXiv:2607. 09826v1 Announce Type: cross Abstract: Dysgraphia is a specific learning disability that is prevalent among school-age children.

By Lydia Ouhib (LIASD), Yassine Ouzar (LIASD), Zo\'e Pinseel (LIASD), St\'ephane Bouilland (LIASD), Mehdi Ammi (LIASD)

rag

arXiv AI

Jul 14

Physics-Informed Structure Anchoring With Capture-Aware Prototype Calibration for Cross-Environment RF Fingerprinting

arXiv:2607. 09760v1 Announce Type: cross Abstract: Radio frequency fingerprint identification (RFFI) uses transmitter-specific hardware imperfections as a physicallayer identity cue for Internet of Things (IoT) devices, but deep RFFI models often degrade when the acquisition environment changes.

By Fengchong Yao, Jianbing Li, Qing Liu, Qikun Liu, Kefeng Song, Haitao Li, Song Wang

rag benchmarks

arXiv AI

Jul 14

First-Order Modal Logic in HOL: Deep and Shallow Embeddings with Automated Faithfulness (Extended Preprint)

arXiv:2607. 10880v1 Announce Type: new Abstract: We extend, in Isabelle/HOL, the deep-and-shallow embedding methodology of our prior work from propositional to first-order modal logic (FML) with constant-domain Kripke semantics.

By Christoph Benzm\"uller, Daniel Kirchner

rag

arXiv AI

Jul 14

JEPA for AI-Native 6G: Predictive Representations and Open Challenges

arXiv:2607. 09798v1 Announce Type: cross Abstract: Sixth-generation (6G) networks are moving toward AI-native operation, where learning modules are embedded across the radio access network (RAN), edge, and core.

By Sheikh Salman Hassan, Irshad A. Meer, Almoatssimbillah Saifaldawla, Yan Kyaw Tun, Mustafa Ozger, Madyan Alsenwi, Nguyen Van Huynh, Woong-Hee Lee, Cedomir Stefanovic, Mathini Sellathurai, Henk Wymeersch, Tharmalingam Ratnarajah

rag diffusion benchmarks

arXiv Machine Learning

Jul 14

Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion

arXiv:2607. 10951v1 Announce Type: new Abstract: We introduce Sticky Jump Diffusions (SJDs), continuous-time Markov processes on $\mathbb R^d$ whose discrete anchors are token embeddings.

By Pascal Jutras-Dub\'e, Patrick Pynadath, Jeremy Lu, Yuan Gao, Ruqi Zhang

rag diffusion safety

arXiv AI

Jul 14

More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning

arXiv:2607. 09825v1 Announce Type: cross Abstract: Robotic manipulation policies rely on pre-trained vision models that give either a global scene embedding or a dense patch grid.

By Yi Li (TU Darmstadt), Alexandre Chapin (LIRIS), Liming Chen (LIRIS), Jan Peters (TU Darmstadt), Alap Kshirsagar (IIT Delhi, ADU)

rag robotics fine-tuning

arXiv AI

Jul 14

MusicMark: A Robust Generative Watermarking Framework for Music Generation

arXiv:2607. 11117v1 Announce Type: cross Abstract: AI music generation has rapidly advanced alongside commercial platforms, raising the need for reliable watermarking for provenance and attribution.

By Seohwan Yun, Jeeyoung Yun, Yongjin Kim, Juyeon Lee, Sungwoong Kim

rag diffusion

arXiv Machine Learning

Jul 14

On the modality gap and the contrastive loss in multi-modal representation learning

arXiv:2607. 10698v1 Announce Type: new Abstract: We study the modality gap in CLIP-style dual-encoder contrastive learning, where image and text embeddings remain misaligned despite being trained in a shared space.

By Fabian Mager, Hiba Nassar, Lars Kai Hansen

rag multimodal benchmarks

arXiv AI

Jul 14

Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

arXiv:2607. 11523v1 Announce Type: cross Abstract: When should an intelligent assistant speak up without being asked?

By Gong Sitong, Tianyu Yan, Caixin Kang, Bo Zheng, Xiang Ruan, Huchuan Lu, Kaipeng Zhang, Yoichi Sato, Yifei Huang

rag agents benchmarks safety

arXiv AI

Jul 14

MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry Waveforms

arXiv:2607. 09749v1 Announce Type: cross Abstract: Foundation models have recently emerged as a powerful paradigm for learning transferable representations from large scale biomedical data, yet existing approaches for physiological waveforms primarily optimize reconstruction or forecasting objectives that do not explicitly preserve clinically meaningful waveform morphology.

By Saiyang Feng, Yuanyun Zhang, Shi Li

rag multimodal safety

arXiv AI

Jul 14

Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification

arXiv:2607. 10588v1 Announce Type: new Abstract: Tasks such as customs tariff classification, export control categorization, and standards-based equipment coding require assigning an input instance to a fine-grained class under an explicit regulatory hierarchy.

By Siyu Wang, Wei Tan, Lulu Chen

llms rag nlp benchmarks

Get the daily briefing