-
This short report presents the 2025 edition of the Java Unit Testing Competition in which four test generation tools (EVOFUZZ, EVOSUITE, BBC, and RANDOOP) were benchmarked on a freshly selected set of 55 Java classes from six different open source projects. Th…
arxiv
Fitsum Kifetew, Lin Yun, Davide Prandi
2025-04-12T10:06:52Z
置信度 0.78
cs.SE
-
The interstellar object 3I/ATLAS (also C/2025 N1 (ATLAS), henceforth, 3I), discovered by the ATLAS Chile telescope on 2025 July 1, was rapidly revealed to be the third known interstellar object (ISO) transiting the solar system, with an incoming velocity at in…
arxiv
T. Marshall Eubanks, Bruce G. Bills, Adam Hibberd, W. Paul Blase 等
2025-08-21T17:59:13Z
置信度 0.78
astro-ph.EPastro-ph.IM
-
Discharge medication recommendation plays a critical role in ensuring treatment continuity, preventing readmission, and improving long-term management for patients with chronic metabolic diseases. This paper present an overview of the CHIP 2025 Shared Task 2 c…
arxiv
Juntao Li, Haobin Yuan, Ling Luo, Tengxiao Lv 等
2025-11-09T05:11:27Z
置信度 0.78
cs.CLcs.AI
-
In this paper, we present our submission to SemEval-2025 Task 8: Question Answering over Tabular Data. This task, evaluated on the DataBench dataset, assesses Large Language Models' (LLMs) ability to answer natural language questions over structured data while…
arxiv
Andreas Evangelatos, Giorgos Filandrianos, Maria Lymperaiou, Athanasios Voulodimos 等
2025-03-01T10:24:42Z
置信度 0.78
cs.CL
-
We report our participation in the SISAP 2025 Indexing Challenge using a novel indexing technique called the Hilbert forest. The method is based on the fast Hilbert sort algorithm, which efficiently orders high-dimensional points along a Hilbert space-filling …
arxiv
Yasunobu Imamura, Takeshi Shinohara, Naoya Higuchi, Kouichi Hirata 等
2025-08-29T14:51:13Z
置信度 0.78
cs.DBcs.DS
-
Traditional voice conversion (VC) methods typically attempt to separate speaker identity and linguistic information into distinct representations, which are then combined to reconstruct the audio. However, effectively disentangling these factors remains challe…
arxiv
Huu Tuong Tu, Huan Vu, cuong tien nguyen, Dien Hy Ngo 等
2025-10-10T07:08:09Z
置信度 0.78
cs.SDeess.AS
-
Pediatric brain tumor segmentation presents unique challenges due to the rarity and heterogeneity of these malignancies, yet remains critical for clinical diagnosis and treatment planning. We propose an ensemble approach integrating nnU-Net, Swin UNETR, and HF…
arxiv
Yuxiao Yi, Qingyao Zhuang, Zhi-Qin John Xu, Xiaowen Wang 等
2025-09-18T03:24:58Z
置信度 0.78
eess.IVcs.CV
-
Browser extensions are additional tools developed by third parties that integrate with web browsers to extend their functionality beyond standard capabilities. However, the browser extension platform is increasingly being exploited by hackers to launch sophist…
arxiv
Shreya Singh, Gaurav Varshney, Tarun Kumar Singh, Vidhi Mishra 等
2025-03-06T10:24:27Z
置信度 0.78
cs.CR
-
In this paper, we present our submission for the token prediction task of EvaCun 2025. Our sys-tems are based on LLMs (Command-R, Mistral, and Aya Expanse) fine-tuned on the task data provided by the organizers. As we only pos-sess a very superficial knowledge…
arxiv
Josef Jon, Ondřej Bojar
2025-10-17T11:47:02Z
置信度 0.78
cs.CL
-
Cone-Beam Computed Tomography (CBCT) and Intraoral Scanning (IOS) are essential for digital dentistry, but annotated data scarcity limits automated solutions for pulp canal segmentation and cross-modal registration. To benchmark semi-supervised learning (SSL) …
arxiv
Yaqi Wang, Zhi Li, Chengyu Wu, Jun Liu 等
2025-12-02T15:29:04Z
置信度 0.78
cs.CV
-
The Medico 2025 challenge addresses Visual Question Answering (VQA) for Gastrointestinal (GI) imaging, organized as part of the MediaEval task series. The challenge focuses on developing Explainable Artificial Intelligence (XAI) models that answer clinically r…
arxiv
Sushant Gautam, Vajira Thambawita, Michael Riegler, Pål Halvorsen 等
2025-08-14T17:43:46Z
置信度 0.78
cs.CVcs.AI
-
This paper presents the third edition of AutoMin, a shared task on automatic meeting summarization into minutes. In 2025, AutoMin featured the main task of minuting, the creation of structured meeting minutes, as well as a new task: question answering (QA) bas…
arxiv
Kartik Shinde, Laurent Besacier, Ondrej Bojar, Thibaut Thonet 等
2025-09-17T08:29:57Z
置信度 0.78
cs.CL
-
Entity linking (EL) for biomedical text is typically benchmarked on English-only corpora with flat mentions, leaving the more realistic scenario of nested and multilingual mentions largely unexplored. We present our system for the BioNNE 2025 Multilingual Biom…
arxiv
Chunyu Li, Xindi Zheng, Siqi Liu
2025-09-10T09:14:25Z
置信度 0.78
cs.CL
-
In this paper, we introduce Narrative Learning, a methodology where models are defined entirely in natural language and iteratively refine their classification criteria using explanatory prompts rather than traditional numerical optimisation. We report on expe…
arxiv
Gregory D. Baker
2025-10-10T07:34:40Z
置信度 0.78
cs.LGcs.AIcs.CL
-
Social media users often make scientific claims without citing where these claims come from, generating a need to verify these claims. This paper details work done by the DS@GT team for CLEF 2025 CheckThat! Lab Task 4b Scientific Claim Source Retrieval which s…
arxiv
Jeanette Schofield, Shuyu Tian, Hoang Thanh Thanh Truong, Maximilian Heil
2025-07-09T05:32:02Z
置信度 0.78
cs.IRcs.CL
-
In this paper we present our submission for the NorSID Shared Task as part of the 2025 VarDial Workshop (Scherrer et al., 2025), consisting of three tasks: Intent Detection, Slot Filling and Dialect Identification, evaluated using data in different dialects of…
arxiv
Jaione Bengoetxea, Mikel Zubillaga, Ekhi Azurmendi, Maite Heredia 等
2024-12-13T12:31:06Z
置信度 0.78
cs.CLcs.AIcs.LG
-
Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains. In conjunction with NTIRE 2025, we organized the 1st CD-FSOD Challenge, aiming to advance the …
arxiv
Yuqian Fu, Xingyu Qiu, Bin Ren, Yanwei Fu 等
2025-04-14T20:17:27Z
置信度 0.78
cs.CVcs.AI
-
Large-scale Language Models (LLMs) have revolutionized human-AI interaction and achieved significant success in the generation of novel ideas. However, current assessments of idea generation overlook crucial factors such as knowledge leakage in LLMs, the absen…
arxiv
Yansheng Qiu, Haoquan Zhang, Zhaopan Xu, Ming Li 等
2025-04-19T05:35:45Z
置信度 0.78
cs.AIcs.CL
-
AI has become one of the most influential research areas over the past decade, with growing applications across multiple disciplines. In management studies, artificial intelligence is increasingly recognized as a driver of innovation, sustainability, and decis…
arxiv
Yassine Sekaki, Abdelhafid Khazzar, Hamza Ziane
2025-08-27T12:53:18Z
置信度 0.78
cs.DL
-
This report details our submission to the Mitotic Domain Generalization (MIDOG) 2025 challenge, which addresses the critical task of mitotic figure detection in histopathology for cancer prognostication. Following the "Bitter Lesson"\cite{sutton2019bitterlesso…
arxiv
Zhuoyan Shen, Esther Bär, Maria Hawkins, Konstantin Bräutigam 等
2025-08-28T16:11:58Z
置信度 0.78
eess.IVcs.CV
-
This paper presents the systems we developed for RIRAG-2025, a shared task that requires answering regulatory questions by retrieving relevant passages. The generated answers are evaluated using RePASs, a reference-free and model-based metric. Our systems use …
arxiv
Ioannis Chasandras, Odysseas S. Chlapanis, Ion Androutsopoulos
2024-12-16T08:54:21Z
置信度 0.78
cs.CL
-
The US Naval Research Laboratory's (NRL's) Autonomous Planning In-space Assembly Reinforcement-learning free-flYer (APIARY) experiment pioneers the use of reinforcement learning (RL) for control of free-flying robots in the zero-gravity (zero-G) environment of…
arxiv
Samantha Chapin, Kenneth Stewart, Roxana Leontie, Carl Glen Henshaw
2025-12-03T12:16:52Z
置信度 0.78
cs.ROcs.LGeess.SY
-
In this report, we present our solution during the participation of the MLCAS 2025 GWFSS Challenge. This challenge hosts a semantic segmentation competition specific to wheat plants, which requires to segment three wheat organs including the head, leaf, and st…
arxiv
Songliang Cao, Tianqi Hu, Hao Lu
2025-08-24T11:14:18Z
置信度 0.78
cs.CV
-
In this paper, we, as the DS@GT team for CLEF 2025 CheckThat! Task 4a Scientific Web Discourse Detection, present the methods we explored for this task. For this multiclass classification task, we determined if a tweet contained a scientific claim, a reference…
arxiv
Ayush Parikh, Hoang Thanh Thanh Truong, Jeanette Schofield, Maximilian Heil
2025-07-08T17:30:18Z
置信度 0.78
cs.CL
-
This report synthesizes the outcomes of a two-day workshop held in Washington, D.C. in May, 2025 that convened researchers, industry representatives, and government stakeholders to examine the current state and future directions of quantum diamond technologies…
arxiv
Danielle A. Braje, Matthew L. Markham, Jennifer M. Schloss, Michael A. Slocum 等
2025-11-14T18:34:27Z
置信度 0.78
quant-phcond-mat.mtrl-sci
-
This is a review article for The Review of Particle Physics 2026 (aka the Particle Data Book), appearing as Chapter 23. It forms a compact review of our understanding of cosmological inflation near the end of 2025. Topics included are Scalar Field Cosmology; P…
arxiv
John Ellis, Vincent Vennin, David Wands
2023-12-20T18:02:33Z
置信度 0.78
astro-ph.COhep-phhep-th
-
This report presents findings from an expert survey on digital minds takeoff scenarios. The survey was conducted in early 2025 with 67 experts in digital minds research, AI research, philosophy, forecasting, and related fields. Participants provided probabilis…
arxiv
Lucius Caviola, Bradford Saad
2025-08-01T11:20:42Z
置信度 0.78
cs.CY
-
This paper presents the results of the 2025 Automatic Music Transcription (AMT) Challenge, an online competition to benchmark progress in multi-instrument transcription. Eight teams submitted valid solutions; two outperformed the baseline MT3 model. The result…
arxiv
Ojas Chaturvedi, Kayshav Bhardwaj, Tanay Gondil, Benjamin Shiue-Hal Chou 等
2026-03-29T05:41:42Z
置信度 0.78
cs.SDcs.IR
-
The year 2024 witnessed accelerated global AI governance advancements, marked by strengthened multilateral frameworks and proliferating national regulatory initiatives. This acceleration underscores an unprecedented need to systematically track governance prog…
arxiv
Yi Zeng, Enmeng Lu, Xiaoyang Guo, Cunqing Huangfu 等
2025-07-10T04:28:27Z
置信度 0.78
cs.CY
-
This paper presents the winning solution for the S23DR Challenge 2025, which involves predicting a house's 3D roof wireframe from a sparse point cloud and semantic segmentations. Our method operates directly in 3D, first identifying vertex candidates from the …
arxiv
Jan Skvrna, Lukas Neumann
2025-06-19T15:56:51Z
置信度 0.78
cs.CV
-
In this paper, we present an overview of ClinIQLink, a shared task, collocated with the 24th BioNLP workshop at ACL 2025, designed to stress-test large language models (LLMs) on medically-oriented question answering aimed at the level of a General Practitioner…
arxiv
Brandon Colelough, Davis Bartels, Dina Demner-Fushman
2025-06-18T19:56:32Z
置信度 0.78
cs.CLcs.AIcs.IR
-
Event-based eye tracking has become a pivotal technology for augmented reality and human-computer interaction. Yet, existing methods struggle with real-world challenges such as abrupt eye movements and environmental noise. Building on the efficiency of the Lig…
arxiv
Hoang M. Truong, Vinh-Thuan Ly, Huy G. Tran, Thuan-Phat Nguyen 等
2025-04-14T07:57:22Z
置信度 0.78
cs.CV
-
In 2025, the UK Office for National Statistics released a novel dataset of monthly inter-industry payment flows during January 2017 to November 2024 at the 5-digit SIC level (ONS, 2025a), covering $>$3.1 million UK organizations. Annual aggregates amount to…
arxiv
Kerstin Hötte
2025-08-25T06:07:39Z
置信度 0.78
econ.GN
-
Complex Video Object Segmentation (VOS) presents significant challenges in accurately segmenting objects across frames, especially in the presence of small and similar targets, frequent occlusions, rapid motion, and complex interactions. In this report, we pre…
arxiv
An Yan, Leilei Cao, Feng Lu, Ran Hong 等
2025-09-18T12:23:51Z
置信度 0.78
cs.CV
-
This report presents an overview of the 7th Large-scale Video Object Segmentation (LSVOS) Challenge held in conjunction with ICCV 2025. Besides the two traditional tracks of LSVOS that jointly target robustness in realistic video scenarios: Classic VOS (VOS), …
arxiv
Chang Liu, Henghui Ding, Kaining Ying, Lingyi Hong 等
2025-10-13T07:02:09Z
置信度 0.78
cs.CV
-
Mechanistic interpretability (MI) seeks to uncover how language models (LMs) implement specific behaviors, yet measuring progress in MI remains challenging. The recently released Mechanistic Interpretability Benchmark (MIB; Mueller et al., 2025) provides a sta…
arxiv
Dana Arad, Yonatan Belinkov, Hanjie Chen, Najoung Kim 等
2025-11-23T11:33:59Z
置信度 0.78
cs.CLcs.AI
-
Room temperature superconductivity, as one of the famous jewels on the crown of physics, has attracted continuous attention and unremitting efforts from numerous scientists. In recent years, more and more reports on room temperature superconductivity evoke man…
arxiv
Huiqian Luo
2025-03-04T02:48:48Z
置信度 0.78
cond-mat.supr-concond-mat.mtrl-scicond-mat.str-el
-
This work examines the findings of the NTIRE 2025 Shadow Removal Challenge. A total of 306 participants have registered, with 17 teams successfully submitting their solutions during the final evaluation phase. Following the last two editions, this challenge ha…
arxiv
Florin-Alexandru Vasluianu, Tim Seizinger, Zhuyun Zhou, Cailian Chen 等
2025-06-18T14:58:49Z
置信度 0.78
cs.CV
-
This report presents our solution to the Ego4D Natural Language Queries (NLQ) Challenge at CVPR 2025. Egocentric video captures the scene from the wearer's perspective, where gaze serves as a key non-verbal communication cue that reflects visual attention and …
arxiv
Wei-Cheng Lin, Chih-Ming Lien, Chen Lo, Chia-Hung Yeh
2025-06-06T06:21:57Z
置信度 0.78
cs.CV
-
Deep learning has driven significant advances in mitotic figure analysis within computational pathology. In this paper, we present our approach to the Mitosis Domain Generalization (MIDOG) 2025 Challenge, which consists of two distinct tasks, i.e., mitotic fig…
arxiv
Shuting Xu, Runtong Liu, Zhixuan Chen, Junlin Hou 等
2025-08-29T15:16:35Z
置信度 0.78
eess.IVcs.CV
-
We have developed a Scalable CI/CD Pipeline to address internal challenges related to Japan 2025 cliff problem, a critical issue where the mass end of service life of legacy core IT systems threatens to significantly increase the maintenance cost and black box…
arxiv
Kuniaki Kudo, Sherine Devi
2025-10-20T11:17:20Z
置信度 0.78
cs.SE
-
The DRAGUN Track at TREC 2025 targets the growing need for effective support tools that help users evaluate the trustworthiness of online news. We describe the UR_Trecking system submitted for both Task 1 (critical question generation) and Task 2 (retrieval-au…
arxiv
Ignacy Alwasiak, Kene Nnolim, Jaclyn Thi, Samy Ateia 等
2026-03-24T12:22:27Z
置信度 0.78
cs.IR
-
We present NightFeats, a structured multi-agent retrieval-augmented generation (RAG) system submitted to the MMU-RAGent competition at NeurIPS 2025, where it was awarded Best Dynamic Evaluation in the text-to-text track. Rather than targeting benchmark maximiz…
arxiv
Quentin Fever, Naziha Aslam
2026-04-21T19:18:07Z
置信度 0.78
cs.CLcs.AIcs.IRcs.LG
-
The development of accurate and efficient machine learning models for predicting the structure and properties of molecular crystals has been hindered by the scarcity of publicly available datasets of structures with property labels. To address this challenge, …
arxiv
Vahe Gharakhanyan, Luis Barroso-Luque, Yi Yang, Muhammed Shuaibi 等
2025-08-04T17:43:22Z
置信度 0.78
physics.chem-ph
-
Numerical claims, statements involving quantities, comparisons, and temporal references, pose unique challenges for automated fact-checking systems. In this study, we evaluate modeling strategies for veracity prediction of such claims using the QuanTemp datase…
arxiv
Maximilian Heil, Aleksandar Pramov
2025-07-08T17:22:22Z
置信度 0.78
cs.CL
-
The Cambrian lattices, introduced in (Reading, 2006), generalize the Tamari lattice to any choice of Coxeter element in any finite Coxeter group. They are further generalized to the m-Cambrian lattices (Stump, Thomas, Williams, 2015). However, their definition…
arxiv
Clément Chenevière, Wenjie Fang, Corentin Henriet
2025-04-18T06:09:26Z
置信度 0.78
math.CO
-
In this report, we present a cross-view multi-modal object segmentation approach for the object correspondence task in the Ego-Exo4D Correspondence Challenges 2025. Given object queries from one perspective (e.g., ego view), the goal is to predict the correspo…
arxiv
Yuqian Fu, Runze Wang, Yanwei Fu, Danda Pani Paudel 等
2025-06-06T08:23:39Z
置信度 0.78
cs.CVcs.AI
-
Large-scale Video Object Segmentation (LSVOS) addresses the challenge of accurately tracking and segmenting objects in long video sequences, where difficulties stem from object reappearance, small-scale targets, heavy occlusions, and crowded scenes. Existing a…
arxiv
Yujie Xie, Hongyang Zhang, Zhihui Liu, Shihai Ruan
2025-09-22T08:30:34Z
置信度 0.78
cs.CV
-
We study the \textsc{Labeled Contractibility} problem, where the input consists of two vertex-labeled graphs $G$ and $H$, and the goal is to determine whether $H$ can be obtained from $G$ via a sequence of edge contractions. Lafond and Marchand~[WADS 2025] ini…
arxiv
Yashaswini Mathur, Prafullkumar Tale
2025-10-07T16:33:44Z
置信度 0.78
cs.DScs.DM
-
Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal scenarios. To address this …
arxiv
Hao Liang, Ruitao Wu, Bohan Zeng, Junbo Niu 等
2025-09-07T14:47:32Z
置信度 0.78
cs.CLcs.CV
-
This report presents the solution and results of our team MSRA\_SC in the Commonsense Persona-Grounded Dialogue Challenge (CPDC 2025). We propose a simple yet effective framework that unifies improvements across both GPU Track and API Track. Our method centers…
arxiv
Yitian Huang, Yuxuan Lei, Jianxun Lian, Hao Liao
2025-11-25T11:24:14Z
置信度 0.78
cs.AI
-
Improving smart grid system management is crucial in the fight against climate change, and enabling consumers to play an active role in this effort is a significant challenge for electricity suppliers. In this regard, millions of smart meters have been deploye…
arxiv
Adrien Petralia, Paul Boniol, Philippe Charpentier, Themis Palpanas
2025-06-06T09:08:34Z
置信度 0.78
cs.LG
-
Gluing theorem for random unitaries [Schuster, Haferkamp, Huang, QIP 2025] have found numerous applications, including designing low depth random unitaries [Schuster, Haferkamp, Huang, QIP 2025], random unitaries in ${\sf QAC0}$ [Foxman, Parham, Vasconcelos, Y…
arxiv
Prabhanjan Ananth, John Bostanci, Aditya Gulati, Yao-Ting Lin
2025-10-05T08:11:33Z
置信度 0.78
cs.CRquant-ph
-
We introduce the AIM 2025 Real-World RAW Image Denoising Challenge, aiming to advance efficient and effective denoising techniques grounded in data synthesis. The competition is built upon a newly established evaluation benchmark featuring challenging low-ligh…
arxiv
Feiran Li, Jiacheng Li, Marcos V. Conde, Beril Besbinar 等
2025-10-08T03:22:42Z
置信度 0.78
cs.CV
-
This report presents the winning solution for Task 1 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery at ECML-PKDD 2025. The task required designing an adversarial attack against a provided classification model tha…
arxiv
Dimitris Stefanopoulos, Andreas Voskou
2025-10-18T10:26:47Z
置信度 0.78
cs.LGcs.CR
-
The legislative output of Colombia's House of Representatives between 2014 and 2025 is analyzed using 4,083 bills. Bipartite networks are constructed between parties and bills, and between representatives and bills, along with their projections, to characteriz…
arxiv
Juan Sosa, Brayan Riveros, Emma J. Camargo-Díaz
2025-12-18T18:06:30Z
置信度 0.78
physics.soc-phstat.COstat.ME
-
The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025, at the University of California, Berkeley, in Berkeley, California, USA. As pa…
arxiv
Emily Alsentzer, Marie-Laure Charpignon, Bill Chen, Niharika D'Souza 等
2025-10-17T00:54:03Z
置信度 0.78
cs.LG
-
Concerns about AI-generated political content are growing, yet there is limited empirical evidence on how deepfakes actually appear and circulate across social platforms during major events in democratic countries. In this study, we present one of the first in…
arxiv
Victor Livernoche, Andreea Musulan, Zachary Yang, Jean-François Godbout 等
2025-12-15T21:49:40Z
置信度 0.78
cs.SI
-
This paper describes the 4th-place solution by team ambitious for the RecSys Challenge 2025, organized by Synerise and ACM RecSys, which focused on universal behavioral modeling. The challenge objective was to generate user embeddings effective across six dive…
arxiv
Sergei Makeev, Alexandr Andreev, Vladimir Baikalov, Vladislav Tytskiy 等
2025-08-09T12:35:52Z
置信度 0.78
cs.IR
-
Despite widespread adoption, the impact of AI tools on software development in the wild remains understudied. We conduct a randomized controlled trial (RCT) to understand how AI tools at the February-June 2025 frontier affect the productivity of experienced op…
arxiv
Joel Becker, Nate Rush, Elizabeth Barnes, David Rein
2025-07-12T00:16:33Z
置信度 0.78
cs.AIcs.HCcs.SE
-
The International Mathematical Olympiad (IMO) is widely regarded as the world championship of high-school mathematics. IMO problems are renowned for their difficulty and novelty, demanding deep insight, creativity, and rigor. Although large language models per…
arxiv
Yichen Huang, Lin F. Yang
2025-07-21T17:59:49Z
置信度 0.78
cs.AI
-
This paper describes our system for SemEval 2025 Task 7: Previously Fact-Checked Claim Retrieval. The task requires retrieving relevant fact-checks for a given input claim from the extensive, multilingual MultiClaim dataset, which comprises social media posts …
arxiv
Amirmohammad Azadi, Sina Zamani, Mohammadmostafa Rostamkhani, Sauleh Eetemadi
2025-03-12T02:59:41Z
置信度 0.78
cs.CL
-
This paper presents an overview of the NTIRE 2025 Image Denoising Challenge (σ = 50), highlighting the proposed methodologies and corresponding results. The primary objective is to develop a network architecture capable of achieving high-quality denoising perf…
arxiv
Lei Sun, Hang Guo, Bin Ren, Luc Van Gool 等
2025-04-16T17:35:09Z
置信度 0.78
cs.CV
-
This paper presents our submission to Task 1, Subjectivity Detection, of the CheckThat! Lab at CLEF 2025. We investigate the effectiveness of transfer-learning and stylistic data augmentation to improve classification of subjective and objective sentences in E…
arxiv
Maximilian Heil, Dionne Bang
2025-07-08T17:18:50Z
置信度 0.78
cs.CLcs.AI
-
This paper presents a comprehensive review of the AIM 2025 Challenge on Inverse Tone Mapping (ITM). The challenge aimed to push forward the development of effective ITM algorithms for HDR image reconstruction from single LDR inputs, focusing on perceptual fide…
arxiv
Chao Wang, Francesco Banterle, Bin Ren, Radu Timofte 等
2025-08-19T03:18:22Z
置信度 0.78
cs.CVeess.IV
-
Multilingual e-commerce search is challenging due to linguistic diversity and the noise inherent in user-generated queries. This paper documents the solution employed by our team (EAR-MP) for the CIKM 2025 AnalytiCup, which addresses two core tasks: Query-Cate…
arxiv
JaeEun Lim, Soomin Kim, Jaeyong Seo, Iori Ono 等
2025-10-27T05:32:13Z
置信度 0.78
cs.IR
-
This volume contains the proceedings of GandALF 2025, the Sixteenth International Symposium on Games, Automata, Logics, and Formal Verification. GandALF 2025 took place on 16-17th September 2025, in Valletta, Malta. The aim of GandALF 2025 is to bring together…
arxiv
Giorgio Bacci, Adrian Francalanza
2025-09-16T17:14:12Z
置信度 0.78
cs.LO
-
While recent neural audio codecs deliver superior speech quality at ultralow bitrates over traditional methods, their practical adoption is hindered by obstacles related to low-resource operation and robustness to acoustic distortions. Edge deployment scenario…
arxiv
Kamil Wojcicki, Yusuf Ziya Isik, Laura Lechler, Mansur Yesilbursa 等
2025-10-27T13:21:30Z
置信度 0.78
cs.SDeess.AS
-
Social media platforms serve as central hubs for content dissemination, opinion expression, and public engagement across diverse modalities. Accurately predicting the popularity of social media videos enables valuable applications in content recommendation, tr…
arxiv
Liliang Ye, Yunyao Zhang, Yafeng Wu, Yi-Ping Phoebe Chen 等
2025-07-01T16:52:20Z
置信度 0.78
cs.CVcs.LGcs.MM
-
This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. The aim of this challenge is to…
arxiv
Shuhao Han, Haotian Fan, Fangyuan Kong, Wenjie Liao 等
2025-05-22T07:12:36Z
置信度 0.78
cs.CVcs.AI
-
This paper presents a comprehensive review of the 1st Challenge on Video Quality Enhancement for Video Conferencing held at the NTIRE workshop at CVPR 2025, and highlights the problem statement, datasets, proposed solutions, and results. The aim of this challe…
arxiv
Varun Jain, Zongwei Wu, Quan Zou, Louis Florentin 等
2025-05-25T05:53:24Z
置信度 0.78
cs.CV
-
Accurate intraoperative image guidance is critical for achieving maximal safe resection in brain tumor surgery, yet neuronavigation systems based on preoperative MRI lose accuracy during the procedure due to brain shift. Aligning post-resection intraoperative …
arxiv
Reuben Dorent, Laura Rigolo, Colin P. Galvin, Junyu Chen 等
2025-08-13T09:31:06Z
置信度 0.78
cs.CV
-
Multi-object tracking (MOT) in sports is highly challenging due to irregular player motion, uniform appearances, and frequent occlusions. These difficulties are further exacerbated by the geometric distortion and extreme scale variation introduced by static fi…
arxiv
Rong-Lin Jian, Ming-Chi Luo, Chen-Wei Huang, Chia-Ming Lee 等
2026-01-31T03:08:48Z
置信度 0.78
cs.CVcs.MM
-
This paper documents GETALP's submission to the Third Run of the Automatic Minuting Shared Task at SIGDial 2025. We participated in Task B: question-answering based on meeting transcripts. Our method is based on a retrieval augmented generation (RAG) system an…
arxiv
Jeongwoo Kang, Markarit Vartampetian, Felix Herron, Yongxin Zhou 等
2025-08-01T09:51:05Z
置信度 0.78
cs.CL
-
As natural language processing for gender bias becomes a significant interdisciplinary topic, the prevalent data-driven techniques, such as pre-trained language models, suffer from biased corpus. This case becomes more obvious regarding those languages with le…
arxiv
Yizhi Li, Ge Zhang, Hanhua Hong, Yiwen Wang 等
2025-06-14T17:06:04Z
置信度 0.78
cs.CL
-
On July 1, 2025, YouTube retired its decade-long public "Trending" pages, ending platform-curated, non-personalized video discovery. The Trending list had long served as a vital lens into algorithmic influence, cultural diffusion, and crisis communication glob…
arxiv
Alexandre Goncalves, Yee Man Margaret Ng
2025-10-24T20:19:16Z
置信度 0.78
cs.SI
-
When AI entered the workplace, many believed it could reshape teamwork as profoundly as it boosted individual productivity. Would AI finally ease the longstanding challenges of team collaboration? Our findings suggested a more complicated reality. We conducted…
arxiv
Qing Xiao, Xinlan Emily Hu, Mark E. Whiting, Arvind Karunakaran 等
2025-09-13T19:32:56Z
置信度 0.78
cs.HCcs.CYcs.SE
-
This paper presents the architecture and performance of a novel Multilingual Automatic Speech Recognition (ASR) system developed by the Transsion Speech Team for Track 1 of the MLC-SLM 2025 Challenge. The proposed system comprises three key components: 1) a fr…
arxiv
Xiaoxiao Li, An Zhu, Youhai Jiang, Fengjie Zhu
2025-08-15T10:39:05Z
置信度 0.78
eess.AScs.AIcs.CL
-
Despite the widespread use of ''artificial intelligence'' (AI) framing in Natural Language Processing (NLP) research, it is not clear what researchers mean by ''intelligence''. To that end, we present the results of a survey on the notion of ''intelligence'' a…
arxiv
Bertram Højer, Terne Sasha Thorn Jakobsen, Anna Rogers, Stefan Heinrich
2025-05-27T09:53:27Z
置信度 0.78
cs.CLcs.CY
-
Physics provides fundamental laws that describe and predict the natural world. AI systems aspiring toward more general, real-world intelligence must therefore demonstrate strong physics problem-solving abilities: to formulate and apply physical laws for explai…
arxiv
Jiahao Qiu, Jingzhe Shi, Xinzhe Juan, Zelin Zhao 等
2025-09-01T17:59:13Z
置信度 0.78
cs.AI
-
The Sign Language Translation and Avatar Technology (SLTAT) workshops continue a series of gatherings to share recent advances in improving deaf / human communication through non-invasive means. This 2025 edition, the 9th since its first appearance in 2011, is…
arxiv
Fabrizio Nunnari, Cristina Luna Jiménez, Rosalee Wolfe, John C. McDonald 等
2025-08-11T14:50:21Z
置信度 0.78
cs.CL
-
Electoral boundaries in Malaysia are not publicly available in machine-readable form. This prevents rigorous analysis of geography-centric issues such as malapportionment and gerrymandering, and constrains spatial perspectives on electoral outcomes. We present…
arxiv
Thevesh Thevananthan, Danesh Prakash Chacko
2025-12-30T13:25:15Z
置信度 0.78
stat.AP
-
The SoccerNet 2025 Challenges mark the fifth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in football video understanding. This year's challenges span four vision-based tasks: (1) Team Ball Action Sp…
arxiv
Silvio Giancola, Anthony Cioppa, Marc Gutiérrez-Pérez, Jan Held 等
2025-08-26T16:37:07Z
置信度 0.78
cs.CV
-
Identifying useful sorbent materials for direct air capture (DAC) from humid air remains a challenge. We present the Open DAC 2025 (ODAC25) dataset, a significant expansion and improvement upon ODAC23 (Sriram et al., ACS Central Science, 10 (2024) 923), compri…
arxiv
Anuroop Sriram, Logan M. Brabson, Xiaohan Yu, Sihoon Choi 等
2025-08-05T07:08:01Z
置信度 0.78
cond-mat.mtrl-scics.LGphysics.chem-ph
-
Referring Video Object Segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This task has attracted increasing attention in the field of computer vision due to its promising applications in video editing and human-…
arxiv
Tianming Liang, Haichao Jiang, Wei-Shi Zheng, Jian-Fang Hu
2025-03-30T16:43:04Z
置信度 0.78
cs.CV
-
This paper introduces DuTerm, a novel two-stage architecture for terminology-constrained machine translation. Our system combines a terminology-aware NMT model, adapted via fine-tuning on large-scale synthetic data, with a prompt-based LLM for post-editing. Th…
arxiv
Akshat Singh Jaswal
2025-11-07T08:50:58Z
置信度 0.78
cs.CLcs.AI
-
Welcome to the eighth edition of the AI Index report. The 2025 Index is our most comprehensive to date and arrives at an important moment, as AI's influence across society, the economy, and global governance continues to intensify. New in this year's report ar…
arxiv
Nestor Maslej, Loredana Fattorini, Raymond Perrault, Yolanda Gil 等
2025-04-08T02:01:37Z
置信度 0.78
cs.AI
-
This study presents a transfer-learning framework based on Convolutional Gated Recurrent Units (ConvGRU) for short-term rainfall prediction in the Weather4Cast 2025 competition. A single SEVIRI infrared channel (10.8 μm wavelength) is used as input, which cons…
arxiv
Anushree Bhuskute, Kaushik Gopalan, Jeet Shah
2025-11-14T11:51:59Z
置信度 0.78
cs.CV
-
Elite football is believed to have evolved in recent years, yet systematic evidence for the pace and form of that change remains sparse. Drawing on event-level records for 13,018 matches across ten top-tier men's and women's leagues in England, Spain, Germany,…
arxiv
Rebecca Carstens, Raj Deshpande, Pau Esteve, Nicolò Fidelibus 等
2025-06-27T10:55:20Z
置信度 0.78
physics.soc-phcs.SI
-
Human identification at a distance (HID) is challenging because traditional biometric modalities such as face and fingerprints are often difficult to acquire in real-world scenarios. Gait recognition provides a practical alternative, as it can be captured reli…
arxiv
Jingzhe Ma, Meng Zhang, Jianlong Yu, Kun Liu 等
2026-02-07T14:22:17Z
置信度 0.78
cs.CV
-
Two-dimensional (2D) materials have shown broad application prospects in fields such as energy, environment, and aerospace owing to their unique electrical, mechanical, thermal and other properties. With the development of artificial intelligence (AI), the dis…
arxiv
Chengbo Li, Ying Wang, Qianying Wang, Zhizhi Tan 等
2025-10-01T11:14:49Z
置信度 0.78
cond-mat.mtrl-sci
-
This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future research directions. The ch…
arxiv
Henghui Ding, Chang Liu, Nikhila Ravi, Shuting He 等
2025-04-15T16:02:47Z
置信度 0.78
cs.CV
-
Using a 100-day symmetric window around the January 2025 U.S. presidential inauguration, non-parametric statistical methods with bootstrap resampling (10,000 iterations) analyze distributional properties and anomalies. Results indicate a statistically signific…
arxiv
Sandy H. S. Herho, Siti N. Kaban, Cahya Nugraha
2025-06-23T15:14:27Z
置信度 0.78
econ.EMstat.AP
-
Fluid movement beneath volcanic regions can influence earthquake activity, but the processes linking seismic and volcanic systems are not fully understood. In early 2025, an unusual seismic sequence occurred close to Santorini, providing new insight into these…
arxiv
E. Lippiello, G. Petrillo, C. Godano, E. Papadimitriou 等
2025-04-30T07:07:50Z
置信度 0.78
physics.geo-ph
-
We report on the observation and measurement of astrometry, photometry, morphology, and activityof the interstellar object 3I/ATLAS, also designated C/2025 N1 (ATLAS) with the NSF-DOE Vera C. Rubin Observatory. Comet 3I/ATLAS, the third known interstellar obje…
arxiv
Colin Orion Chandler, Pedro H. Bernardinelli, Mario Jurić, Devanshi Singh 等
2025-07-17T06:23:27Z
置信度 0.78
astro-ph.EPastro-ph.GA
-
Clinical documentation increasingly uses automatic speech recognition and summarization, yet converting conversations into actionable medical orders for Electronic Health Records remains unexplored. A solution to this problem can significantly reduce the docum…
arxiv
Jean-Philippe Corbeil, Asma Ben Abacha, Jerome Tremblay, Phillip Swazinna 等
2025-10-30T19:56:05Z
置信度 0.78
cs.CLcs.AI
-
This paper presents the Low-Complexity Acoustic Scene Classification with Device Information Task of the DCASE 2025 Challenge, along with its baseline system. Continuing the focus on low-complexity models, data efficiency, and device mismatch from previous edi…
arxiv
Florian Schmid, Paul Primus, Toni Heittola, Annamaria Mesaros 等
2025-05-03T08:52:18Z
置信度 0.78
eess.AScs.SD
-
This paper describes the system submitted by Team A to SemEval 2025 Task 11, ``Bridging the Gap in Text-Based Emotion Detection.'' The task involved identifying the perceived emotion of a speaker from text snippets, with each instance annotated with one of six…
arxiv
P Sam Sahil, Anupam Jamatia
2025-02-27T07:59:01Z
置信度 0.78
cs.CL
-
This paper presents an overview of the NTIRE 2025 Challenge on UGC Video Enhancement. The challenge constructed a set of 150 user-generated content videos without reference ground truth, which suffer from real-world degradations such as noise, blur, faded colo…
arxiv
Nikolay Safonov, Alexey Bryncev, Andrey Moskalenko, Dmitry Kulikov 等
2025-05-05T20:06:11Z
置信度 0.78
cs.CV
-
In this work we examine the 2025 DESI analysis of dark energy, which suggests that dark energy is evolving in time with an increasing equation of state $w$. We explore a wide range of quintessence models, described by a potential function $V(\varphi)$, includi…
arxiv
Husam Adam, Mark P. Hertzberg, Daniel Jiménez-Aguilar, Iman Khan
2025-09-16T17:55:24Z
置信度 0.78
astro-ph.COgr-qchep-phhep-th