The paper introduces Image Bundle Composition (IBC), a new paradigm that moves beyond point-wise image matching to dynamically assemble cohesive image bundles from large, unstructured photo collections. It presents IBCBench, a benchmark with over 109,000 images and 667 verified queries, and proposes BundleWeaver, an agentic framework that uses a Large Language Model for relational role discovery and a Vision‑Language Model for bundle verification. Experiments show that BundleWeaver outperforms existing embedding and decompose‑and‑rerank methods, underscoring the importance of relational composition over atomic scoring.
By Rong Shan, Tianyi Xu, Congmin Zheng, Wenteng Chen, Jiachen Zhu, Junjie Wu, Teng Wang, Weiwen Liu, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin
arXiv:2608.30345v1 Announce Type: new
Abstract: Generating multiple diverse and high-quality solutions is valuable for many applications, such as code-test generation and drug discovery. However, Lar...
By Yi Fang, Que Shen, Chengpeng Li, Boyi Deng, Wei Shi, Wenjie Wang, Fuli Feng, Fengli Xu, Dayiheng Liu
arXiv:2608.30498v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable success in STEM domains, where progress is often driven by vertical, step-by-step deduct...
By Qi Li, Zhaojie Kang, Yingjie He, Zheng Lin, Hao Zhang, Guangxin Wu, Yan Gong, Rong Fu, Jianyuan Ni
arXiv:2608.31082v1 Announce Type: new
Abstract: Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI...
By Milad Rezaei Hajidehi, Qitong Wang, Stratos Idreos
arXiv:2608.28611v1 Announce Type: cross
Abstract: Recent advances in large language models (LLMs) like ChatGPT and LLaMA have transformed AI-driven education, but these systems are predominantly trai...
By Isha Narang, Sneh Gosai, Mayank Singh
E‑SENS is a training‑free reranking technique designed to improve negative‑constraint retrieval in retrieval‑augmented language models. It works by extracting a compact ‘trap query’ that represents the excluded concept and subtracting the similarity of this trap query from the original retrieval score, thereby reducing the influence of documents that mention the excluded concept. Experiments on the ExcluIR benchmark demonstrate that E‑SENS achieves a clear recall‑violation trade‑off across four embedding models and effectively reduces trap retrieval while preserving recall.
By Yerang Kim, Jiyoon Myung, Joohyung Han
arXiv:2608.29001v1 Announce Type: new
Abstract: In a data-driven world, efficiently organizing and mapping relationships between objects is crucial. Graphs are powerful tools for modeling these conne...
By Thiago C\'esar Castilho Almeida, Gustavo Rosseto Let\'icio, Lucas Pascotti Valem, Andr\'e Freitas, Daniel Carlos Guimar\~aes Pedronette
arXiv:2608.30315v1 Announce Type: new
Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lang...
By Junjie Yao, Liangkai Hang, Zhi-Qin John Xu
arXiv:2608.29899v1 Announce Type: cross
Abstract: Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models...
By Devrim \c{C}avu\c{s}o\u{g}lu, Emre Akba\c{s}
The next generation of mobile networks is envisioned as fully AI-native, with AI-RAN architectures embedding small language models (SLMs) to perform reasoning over real-time telemetry. The state-of-th...
Retrieval-augmented generation (RAG) systems rely on external corpora that may contain outdated, contradictory, noisy, or unreliable documents, introducing reliability risks. Prior work has leveraged...
General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We introduce AVA, a systematic framework for evaluat...
Scientific discovery often requires reasoning over competing hypotheses that are consistent with experimental observations. For mixed-variable and combinatorial hypothesis spaces, however, constructin...
The article discusses how an FAQ can invert the traditional Retrieval-Augmented Generation (RAG) pipeline. It explains that parsing becomes trivial, retrieval functions as a cache, and few‑shot prompting is reframed as a retrieval problem. The piece highlights the practical implications of designing a corpus around an FAQ structure for enterprise document intelligence.
By Kezhan Shi
Multimodal models often build on architectures designed for generative vision-language modeling, typically combining separately pretrained vision encoders with causal language models. Visual document...
The article outlines a framework for constructing Retrieval-Augmented Generation (RAG) pipelines that progressively add complexity as needed to address observed failure modes. It begins with basic lexical and hybrid search techniques, then incorporates reranking and agentic information‑seeking strategies to improve performance. The approach emphasizes that more sophisticated components should only be introduced when simpler methods prove insufficient.
By Tahreem Rasul
With the development of large language models (LLMs), generative retrieval is becoming increasingly important in e-commerce scenarios. Current mainstream approaches typically use a two-stage training...
Large language models (LLMs) are built from structured high-dimensional objects such as token representations, weights, adaptation updates, caches, and activations, whose multilinear structure is unde...
Multimodal Large Language Models (MLLMs) have shown remarkable success in STEM domains, where progress is often driven by vertical, step-by-step deduction under relatively stable symbol systems. Their...
The unprecedented surge in Earth observation data volume and diversity has exposed a critical bottleneck for traditional manual workflows, catalyzing the emergence of Remote Sensing (RS) Agents. Howev...