Expertini Research Research

Browse Research Papers

46,580+ open-access research outputs.

โœ• Clear
๐Ÿ” avoidance learning ๐Ÿ“‚ Computer Science
Showing 46580 results for "avoidance learning" in Computer Science
Computer Science Preprint PDF DOI

Robust Hybrid Beamforming with Liquid Crystal Antennas and Liquid Neural Networks

Xinquan Wang, Mingjun Ying, Hongren Chen, Guanyue Qian, Xingchen Liu, Peijie Ma, Dipankar Shakya, Christos Argyropoulos, Theodore S. Rappaport ยท 2026

Sub-terahertz (sub-THz) multi-user multiple-input multiple-output (MU-MIMO) systems unlock immense bandwidth for 6G wireless communications. However, practical deployment of wireless systems in sub-THโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment

Mohamed Darwish Mounis, Mohamed Mahmoud, Shaimaa Sedek, Mahmoud Abdalla, Mahmoud SalahEldin Kasem, Abdelrahman Abdallah, Hyun-Soo Kang ยท 2026

Multimodal retrieval systems struggle to resolve image-text queries against text-only corpora: the best vision-language encoder achieves only 27.6 nDCG@10 on MM-BRIGHT, underperforming strong text-onlโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking

Chao Zhang, Shuai Lin, ChengLei Dai, Ye Qian, Fan Mingyang, Yi Zhang, Yi Wang, Jingwei Zhuo ยท 2026

Kuaishou serves over 400 million daily active users, processing hundreds of millions of search queries daily against a repository of tens of billions of short videos. As the final decision layer, the โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment

Hao Yang, Yifan Ji, Zhipeng Xu, Zhenghao Liu, Yukun Yan, Zulong Chen, Shuo Wang, Yu Gu, Ge Yu ยท 2026

Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections. Existing methods often employ Vision-Language Models (VLMs) to encode queries andโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Energy Saving for Cell-Free Massive MIMO Networks: A Multi-Agent Deep Reinforcement Learning Approach

Qichen Wang, Keyu Li, Ozan Alp Topal, Ozlem Tugfe Demir, Mustafa Ozger, Cicek Cavdar ยท 2026

This paper focuses on energy savings in downlink operation of cell-free massive MIMO (CF mMIMO) networks under dynamic traffic conditions. We propose a multi-agent deep reinforcement learning (MADRL) โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

DDP-SA: Scalable Privacy-Preserving Federated Learning via Distributed Differential Privacy and Secure Aggregation

Wenjing Wei, Farid Nait-Abdesselam, Alla Jammine ยท 2026

This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Workmanship of Learning: Embedding Craftsmanship Values in AI-Integrated Educational Tools

Tuan-Ting Huang, Janet Yi-Ching Huang, Stephan Wensveen ยท 2026

Generative AI's emphasis on automation and efficiency challenges design education, where learning is grounded in exploration, reflection, and responsibility. This work introduces AI Craftsmanship, a vโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Leveraging Artist Catalogs for Cold-Start Music Recommendation

Yan-Martin Tamm, Gregor Meehan, Vojtech Nekl, Vojtech Vancura, Rodrigo Alves, Johan Pauwels, Anna Aljanaki ยท 2026

The item cold-start problem poses a fundamental challenge for music recommendation: newly added tracks lack the interaction history that collaborative filtering (CF) requires. Existing approaches ofteโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval

Roxana Petcu, Evangelos Kanoulas, Maarten de Rijke ยท 2026

Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved inโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Evaluating PQC KEMs, Combiners, and Cascade Encryption via Adaptive IND-CPA Testing Using Deep Learning

Simon Calderon, Niklas Johansson, Onur Gunlu ยท 2026

Ensuring ciphertext indistinguishability is fundamental to cryptographic security, but empirically validating this property in real implementations and hybrid settings presents practical challenges. Tโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Data Leakage in Automotive Perception: Practitioners' Insights

Md Abu Ahammed Babu, Sushant Kumar Pandey, Darko Durisic, Andras Balint, Miroslaw Staron ยท 2026

Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliability of machine learning (ML) models in safety-crโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitization

Shunan Zhu, Jiawei Chen, Yonghao Yu, Hideya Ochiai ยท 2026

As high quality public data becomes scarce, Federated Learning (FL) provides a vital pathway to leverage valuable private user data while preserving privacy. However, real-world client data often contโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Beyond Pessimism: Offline Learning in KL-regularized Games

Yuheng Zhang, Claire Chen, Nan Jiang ยท 2026

We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized under a KL constraint to a fixed reference policy. Prior work relies on pessimistic value estimationโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Better Balance in Informatics 2.0: The First-Year Students

Ine Arvola, Rakel H{aa}ndlykken, Elisavet Kozyri ยท 2026

Diversity among computer scientists and technologists is necessary for the sustainable development of society through technological innovation. At UiT The Arctic University of Norway, only 13% of compโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation

Yanan Cao, Ashish Ranjan, Sinduja Subramaniam, Evren Korpeoglu, Kaushiki Nag, Kannan Achan ยท 2026

Repurchase behavior is a primary signal in large-scale retail recommendation, particularly in categories with frequent replenishment: many items in a user's next basket were previously purchased, and โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Label Leakage Attacks in Machine Unlearning: A Parameter and Inversion-Based Approach

Weidong Zheng, Kongyang Chen, Yao Huang, Yuanwei Guo, Yatie Xiao ยท 2026

With the widespread application of artificial intelligence technologies in face recognition and other fields, data privacy security issues have received extensive attention, especially the \textit{rigโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

RPM-Net Reciprocal Point MLP Network for Unknown Network Security Threat Detection

Jiachen Zhang, Yueming Lu, Fan Feng, Zhanfeng Wang, Shengli Pan, Daoqi Han ยท 2026

Effective detection of unknown network security threats in multi-class imbalanced environments is critical for maintaining cyberspace security. Current methods focus on learning class representations โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Sparsity-Aware Roofline Models for Sparse Matrix-Matrix Multiplication

Matthew Qian, Yahia Ramadan, Suhita Anubha, Ariful Azad ยท 2026

Sparse matrix-dense matrix multiplication (SpMM) is a critical kernel in scientific computing, graph analytics, and machine learning, whose performance is often constrained by memory bandwidth. In thiโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract Screening

Yuki Kataoka, Masahiro Banno, Michihito Kyo, Shuri Nakao, Tomoo Sato, Shunsuke Taito, Tomohiro Takayama, Takahiro Tsuge, Yasushi Tsujimoto, Ryuhei So, Toshi A. Furukawa ยท 2026

Background: Server-based screening tools impose subscription costs, while open-source alternatives require coding skills. Objectives: We developed a browser extension that provides no-code, serverlessโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

The Theorems of Dr. David Blackwell and Their Contributions to Artificial Intelligence

Napoleon Paxton ยท 2026

Dr. David Blackwell was a mathematician and statistician of the first rank, whose contributions to statistical theory, game theory, and decision theory predated many of the algorithmic breakthroughs tโ€ฆ

Read Paper โ†’
โ† Prev Page 26 of 2329 Next โ†’