The explosive growth of user-generated video content on online platforms is accompanied by the emergence of numerous near-duplicate videos--videos that are identical or highly similar but differ by partial edits. These duplicates degrade user experience and increase storage and bandwidth costs, making large-scale video deduplication a critical task.
Enterprise Document Intelligence [Vol. 1 #5A] - Document signals (metadata, native TOC, source software) and page-level content (text vs scans, tables, images, columns, page profile) The post Beyond extract_text: The Two Layers of a PDF That Drive RAG Quality appeared first on Towards Data Science .
By Kezhan Shi
This paper presents our solution to the 2026 SoccerNet VQA Challenge. We first develop a cost-effective data synthesis pipeline driven by a Vision-Language Model (VLM), which systematically restructures raw domain data into diverse VQA samples, including concise answers and long-form responses.
The conventional approach to deep learning over relational databases applies neural models, such as Graph Neural Networks (GNNs), to a graph representation of the database. Recent approaches instead operate on databases directly, associating tuples with embeddings and extending query mechanisms to jointly process embeddings and relational content.
Audio watermarking aims to embed identifiable information into audio while remaining imperceptible. Existing methods adopt high-fidelity, low-energy designs to preserve perceptual quality, but the resulting watermarks lack robustness under suppression by speech reconstruction models.
Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential. Realizing this potential requires systematic and scalable methods for evaluating creativity across diverse tasks.
arXiv:2605. 26702v2 Announce Type: replace-cross Abstract: Reliable watermarking of panoramic imagery is fundamentally challenged by arbitrary 3D rotations.
By Pengzhen Chen, Yanwei Liu, Xiaoyan Gu, Antonios Argyriou, Wu Liu, Weiping Wang
arXiv:2606. 10295v1 Announce Type: cross Abstract: The Gromov--Wasserstein (GW) distance provides a framework for comparing metric measure spaces, regardless of their underlying structure or geometry.
By Kaitlyn Hohmeier, Nicolas Fraiman, Caroline Moosmueller
arXiv:2606. 10392v1 Announce Type: new Abstract: Financial named-entity recognition (NER) is essential for translating unstructured financial reports and news into structured knowledge graphs.
By Wu Yuerong, Mingni Luo
arXiv:2606. 09893v1 Announce Type: cross Abstract: Diffusion MRI (dMRI) tractography is the only noninvasive approach for mapping white-matter pathways in the living human brain.
By Guikun Chen, Yuqian Chen, Yijie Li, Yogesh Rathi, Nikos Makris, Fan Zhang, Wenguan Wang, Lauren J. O'Donnell
arXiv:2602. 19393v2 Announce Type: replace Abstract: Steck, Ekanadham, and Kallus [arXiv:2403.
By Taha Bouhsine
arXiv:2604. 07085v2 Announce Type: replace Abstract: In electronic health records (EHRs), clustering patients and distinguishing disease subtypes are key tasks to elucidate pathophysiology and aid clinical decision-making.
By Manar D. Samad, Yina Hou, Shrabani Ghosh
arXiv:2606. 09917v1 Announce Type: new Abstract: Multivariate time series forecasting requires capturing the continuously evolving correlation structure among interacting variables.
By Xingsheng Chen, Siu-Ming Yiu
arXiv:2606. 10829v1 Announce Type: cross Abstract: Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration, but this parallelism is fragile: positions that are individually confident may be unsafe to commit together when their predictions are coupled.
By Yusuf Sahin, Ahmed Rockey Saikia, Volkan Cevher, Paolo Favaro
arXiv:2604. 04287v2 Announce Type: replace Abstract: Foundation models in genomics have shown mixed success compared to their counterparts in natural language processing.
By Maxime Rochkoulets, Lovro Vr\v{c}ek, Mile \v{S}iki\'c
arXiv:2606. 10254v1 Announce Type: new Abstract: While Large Language Models (LLMs) have achieved near-perfect performance in \emph{solving} high-school mathematics, their ability to \emph{evaluate} the diverse reasoning processes of real human students remains under-examined.
By Yiteng Mao, Kenan Xu, Yijia Lyu, Wenhao Li, Jianlong Chen, Xiangfeng Wang
arXiv:2606. 10716v1 Announce Type: cross Abstract: Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich contextualized representations.
By Roberto Mart\'inez-Cruz, Alvaro J. L\'opez-L\'opez, Jos\'e Portela
arXiv:2502. 01272v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks.
By Chang Liu, Hai Huang, Yujie Xing, Xingquan Zuo
arXiv:2605. 18271v2 Announce Type: replace-cross Abstract: With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and responsiveness.
By Changmin Lee, Jaemin Kim, Taesik Gong
arXiv:2606. 10475v1 Announce Type: cross Abstract: Multi-agent debate frameworks have been shown to improve large language model performance in convergent tasks, but they are currently optimized in a way that heavily favors final output accuracy rather than stability of the process.
By Jakub Mas{\l}owski, Jaros{\l}aw A. Chudziak