Qwen Councils
arXiv could not process that search. Try a simpler keyword search or an arXiv field query such as all:quantum.
Showing downloaded papers while arXiv is unavailable.

Computer Science

arXiv preprints from January 1, 2026 through September 24, 2026 — 04:25:17 EST

0

Posted in cs.CL · 2026-01-10 · Sebastian Nehrdich, Kurt Keutzer

MITRA: A Large-Scale Parallel Corpus and Multilingual Pretrained Language Model for Machine Translation and Semantic Retrieval for Pāli, Sanskrit, Buddhist Chinese, and Tibetan

Ancient Buddhist literature features frequent, yet often unannotated, textual parallels spread across diverse languages: Sanskrit, Pāli, Buddhist Chinese, Tibetan, and more. The scale of this material makes manual examination prohibitive. We present the MITRA framework, which consists of a novel pipeline for multilingual parallel...

💬 0 commentsarXiv:2601.06400v1PDF
0

Posted in cs.CL · 2026-01-10 · Hao Yu, Tianyi Xu, Michael A. Hedderich, Wassim Hamidouche, Syed Waqas Zamir, David Ifeoluwa Adelani

AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages

Large language models (LLMs) are increasingly multilingual, yet open models continue to underperform relative to proprietary systems, with the gap most pronounced for African languages. Continued pre-training (CPT) offers a practical route to language adaptation, but improvements on demanding capabilities such as mathematical...

💬 0 commentsarXiv:2601.06395v3PDF
0

Posted in cs.CV · 2026-01-10 · Ahmed Abdelkawy, Ahmed Elsayed, Asem Ali, Aly Farag, Thomas Tretter, Michael McIntyre

Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification

Understanding student behavior in the classroom is essential to improve both pedagogical quality and student engagement. Existing methods for predicting student engagement typically require substantial annotated data to model the diversity of student behaviors, yet privacy concerns often restrict researchers to their own proprietary...

💬 0 commentsarXiv:2601.06394v4PDF
0

Posted in cs.CV · 2026-01-10 · Saksham Singh Kushwaha, Sayan Nag, Yapeng Tian, Kuldeep Kulkarni

Object-WIPER : Training-Free Object and Associated Effect Removal in Videos

In this paper, we introduce Object-WIPER, a training-free framework for removing dynamic objects and their associated visual effects from videos, and inpainting them with semantically consistent and temporally coherent content. Our approach leverages a pre-trained text-to-video diffusion transformer (DiT). Given an input video, a...

💬 0 commentsarXiv:2601.06391v2PDF
0

Posted in cs.IR · 2026-01-10 · Ramnath Kumar, Prateek Jain, Cho-Jui Hsieh

FastLane: Efficient Routed Systems for Late-Interaction Retrieval

Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with Approximate Nearest Neighbor Search (ANNS). We introduce FastLane, a novel retrieval framework that dynamically routes queries to their most informative...

💬 0 commentsarXiv:2601.06389v2PDF
0

Posted in cs.NE · 2026-01-10 · Ke Shang, Hisao Ishibuchi, Zexuan Zhu, Qingfu Zhang

An Efficient Evolutionary Algorithm for Few-for-Many Optimization

Few-for-many (F4M) optimization, recently introduced as a novel paradigm in multi-objective optimization, aims to find a small set of solutions that effectively handle a large number of conflicting objectives. Unlike traditional many-objective optimization methods, which typically attempt comprehensive coverage of the Pareto front,...

💬 0 commentsarXiv:2601.06387v1PDF
0

Posted in cs.CR · 2026-01-10 · Wenjin Yang, Ni Ding, Zijian Zhang, Jing Sun, Zhen Li, Yan Wu, Jiahang Sun, Haotian Lin, Yong Liu, Jincheng An, Liehuang Zhu

Noise Reduction for Pufferfish Privacy: A Practical Noise Calibration Method

This paper introduces a relaxed noise calibration method to enhance data utility while attaining pufferfish privacy. This work builds on the existing $1$-Wasserstein (Kantorovich) mechanism by alleviating the existing overly strict condition that leads to excessive noise, and proposes a practical mechanism design algorithm as a...

💬 0 commentsarXiv:2601.06385v1PDF
0

Posted in cs.MA · 2026-01-10 · Philipp Altmann, Thomy Phan, Maximilian Zorn, Claudia Linnhoff-Popien, Sven Koenig

Dynamic Incentivized Cooperation under Changing Rewards

Peer incentivization (PI) is a popular multi-agent reinforcement learning approach where all agents can reward or penalize each other to achieve cooperation in social dilemmas. Despite their potential for scalable cooperation, current PI methods heavily depend on fixed incentive values that need to be appropriately chosen with respect...

💬 0 commentsarXiv:2601.06382v1PDF
0

Posted in cs.LG · 2026-01-10 · Thomas Vaitses Fontanari, Mariana Recamonde-Mendoza

Hierarchical Pooling and Explainability in Graph Neural Networks for Tumor and Tissue-of-Origin Classification Using RNA-seq Data

This study explores the use of graph neural networks (GNNs) with hierarchical pooling and multiple convolution layers for cancer classification based on RNA-seq data. We combine gene expression data from The Cancer Genome Atlas (TCGA) with a precomputed STRING protein-protein interaction network to classify tissue origin and...

💬 0 commentsarXiv:2601.06381v1PDF
0

Posted in cs.GR · 2026-01-10 · Hao Zhang, Jiahao Luo, Bohui Wan, Yizhou Zhao, Zongrui Li, Michael Vasilkovsky, Chaoyang Wang, Jian Wang, Narendra Ahuja, Bing Zhou

RigMo: Unifying Rig and Motion Learning for Generative Animation

Despite significant progress in 4D generation, rig and motion, the core structural and dynamic components of animation are typically modeled as separate problems. Existing pipelines rely on ground-truth skeletons and skinning weights for motion generation and treat auto-rigging as an independent process, undermining scalability and...

💬 0 commentsarXiv:2601.06378v1PDF
0

Posted in cs.AI · 2026-01-10 · Ningning Zhang, Xingxing Yang, Zhizhong Tan, Weiping Deng, Wenyong Wang

HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents

Although long-term memory systems have made substantial progress in recent years, they still exhibit clear limitations in adaptability, scalability, and self-evolution under continuous interaction settings. Inspired by cognitive theories, we propose HiMem, a hierarchical long-term memory framework for long-horizon dialogues, designed...

💬 0 commentsarXiv:2601.06377v1PDF
0

Posted in cs.MA · 2026-01-10 · Yutong Song, Jiang Wu, Kazi Sharif, Honghui Xu, Nikil Dutt, Amir Rahmani

DemMA: Dementia Multi-Turn Dialogue Agent with Expert-Guided Reasoning and Action Simulation

Simulating dementia patients with large language models (LLMs) is challenging due to the need to jointly model cognitive impairment, emotional dynamics, and nonverbal behaviors over long conversations. We present DemMA, an expert-guided dementia dialogue agent for high-fidelity multi-turn patient simulation. DemMA constructs...

💬 0 commentsarXiv:2601.06373v1PDF
0

Posted in cs.CL · 2026-01-10 · Martha Larson

Talking to Extraordinary Objects: Folktales Offer Analogies for Interacting with Technology

Speech and language are valuable for interacting with technology. It would be ideal to be able to decouple their use from anthropomorphization, which has recently met an important moment of reckoning. In the world of folktales, language is everywhere and talking to extraordinary objects is not unusual. This overview presents examples...

💬 0 commentsarXiv:2601.06372v1PDF
0

Posted in cs.CR · 2026-01-10 · Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang

From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum

To improve the quality of Differentially private (DP) synthetic images, most studies have focused on improving the core optimization techniques (e.g., DP-SGD). Recently, we have witnessed a paradigm shift that takes these techniques off the shelf and studies how to use them together to achieve the best results. One notable work is...

💬 0 commentsarXiv:2601.06368v1PDF
0

Posted in cs.NI · 2026-01-10 · David Hay, Mary Hogan, Shir Landau Feibish

ReAct: Reflection Attack Mitigation For Asymmetric Routing

Amplification Reflection Distributed Denial-of-Service (AR-DDoS) attacks remain a formidable threat, exploiting stateless protocols to flood victims with illegitimate traffic. Recent advances have enabled data-plane defenses against such attacks, but existing solutions typically assume symmetric routing and are limited to a single...

💬 0 commentsarXiv:2601.06367v1PDF
0

Posted in cs.CR · 2026-01-10 · Pratyush Desai, Luoxi Tang, Yuqiao Meng, Zhaohan Xi

SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use

Large Language Models (LLMs) are transforming enterprise workflows but introduce security and ethics challenges when employees inadvertently share confidential data or generate policy-violating content. This paper proposes SafeGPT, a two-sided guardrail system preventing sensitive data leakage and unethical outputs. SafeGPT integrates...

💬 0 commentsarXiv:2601.06366v3PDF
0

Posted in cs.HC · 2026-01-10 · Xiaotian Zhang, Jinhong Yu, Pengwei Yan, Le Jiang, Xingyi Shen, Mumo Cheng, Xiaozhong Liu

Human-in-the-Loop Interactive Report Generation for Chronic Disease Adherence

Chronic disease management requires regular adherence feedback to prevent avoidable hospitalizations, yet clinicians lack time to produce personalized patient communications. Manual authoring preserves clinical accuracy but does not scale; AI generation scales but can undermine trust in patient-facing contexts. We present a...

💬 0 commentsarXiv:2601.06364v1PDF
0

Posted in cs.AI · 2026-01-10 · Yutong Song, Jiang Wu, Shaofan Yuan, Chengze Shen, Jian Wang, Yu Wang, Nikil Dutt, Amir M. Rahmani

Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs

Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the user-specific characteristics that personalization methods aim to preserve. We call this failure mode personalization collapse: explicit style control can conflict with implicit user...

💬 0 commentsarXiv:2601.06362v2PDF
0

Posted in cs.CL · 2026-01-10 · Jakub Dec, Michał Dolina, Stanisław Drożdż, Jarosław Kwapień, Jin Liu, Tomasz Stanisz

Average shortest-path length in word-adjacency networks: Chinese versus English

Complex networks provide powerful tools for analyzing and understanding the intricate structures present in various systems, including natural language. Here, we analyze topology of growing word-adjacency networks constructed from Chinese and English literary works written in different periods. Unconventionally, instead of considering...

💬 0 commentsarXiv:2601.06361v1PDF
0

Posted in cs.CL · 2026-01-10 · Jun-Qi Chen, Kun Zhang, Rui Zheng, Ying Zhong

Mechanism-Faithful Queueing Simulation Model Translation with Large Language Model Support

Queueing simulation studies often require substantial manual effort to translate conceptual system descriptions into executable programs and to verify that the implemented mechanisms match the intended queueing logic. Although large language models (LLMs) may produce executable scripts, executability alone is insufficient when...

💬 0 commentsarXiv:2601.06543v2PDF
0

Posted in cs.CV · 2026-01-10 · Wiktor Mucha, Michael Wray, Martin Kampel

Towards Egocentric 3D Hand Pose Estimation in Unseen Domains

We present V-HPOT, a novel approach for improving the cross-domain performance of 3D hand pose estimation from egocentric images across diverse, unseen domains. State-of-the-art methods demonstrate strong performance when trained and tested within the same domain. However, they struggle to generalise to new environments due to limited...

💬 0 commentsarXiv:2601.06537v1PDF
0

Posted in cs.CL · 2026-01-10 · Dennis Zyska, Alla Rozovskaya, Ilia Kuznetsov, Iryna Gurevych

Exposía: Teaching and Assessment of Academic Writing Skills for Research Project Proposals and Peer Feedback

We present Exposía, the first public dataset that connects writing and feedback in higher education, enabling research on educationally grounded computational approaches to teaching and evaluating academic writing. Exposía includes student research project proposals and peer and instructor feedback consisting of comments and free-text...

💬 0 commentsarXiv:2601.06536v2PDF
0

Posted in cs.MS · 2026-01-10 · Michal Habera, Andreas Zilian

Automated dimensional analysis for PDEs

Physical units are fundamental to scientific computing. However, many finite element frameworks lack built-in support for dimensional analysis. In this work, we present a systematic framework for integrating physical units into the Unified Form Language (UFL). We implement a symbolic \texttt{Quantity} class to track units within...

💬 0 commentsarXiv:2601.06535v2PDF
0

Posted in cs.LG · 2026-01-10 · Qi Dong, Rubing Huang, Ling Zhou, Dave Towey, Jinyu Tian, Jianzhou Wang

Short-term electricity load forecasting with multi-frequency reconstruction diffusion

Diffusion models have emerged as a powerful method in various applications. However, their application to Short-Term Electricity Load Forecasting (STELF) -- a typical scenario in energy systems -- remains largely unexplored. Considering the nonlinear and fluctuating characteristics of the load data, effectively utilizing the powerful...

💬 0 commentsarXiv:2601.06533v1PDF
0

Posted in cs.LG · 2026-01-10 · Bowen Zhang, Hongda Tian, Adam Berry, A. Craig Roussac

Improving Day-Ahead Grid Carbon Intensity Forecasting by Joint Modeling of Local-Temporal and Cross-Variable Dependencies Across Different Frequencies

Accurate forecasting of the grid carbon intensity factor (CIF) is critical for enabling demand-side management and reducing emissions in modern electricity systems. Leveraging multiple interrelated time series, CIF prediction is typically formulated as a multivariate time series forecasting problem. Despite advances in deep...

💬 0 commentsarXiv:2601.06530v1PDF