Expertini Research Research

Browse Research Papers

346,661+ open-access research outputs.

โœ• Clear
๐Ÿ” avoidance learning
Showing 346661 results for "avoidance learning"
AI & Data Science Preprint PDF DOI

Sustained Gradient Alignment Mediates Subliminal Learning in a Multi-Step Setting: Evidence from MNIST Auxiliary Logit Distillation Experiment

Chayanon Kitkana, Shivam Arora ยท 2026

In the MNIST auxiliary logit distillation experiment, a student can acquire an unintended teacher trait despite distilling only on no-class logits through a phenomenon called subliminal learning. Undeโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Measuring the Sensitivity of Classification Models with the Error Sensitivity Profile

Andrea Maurino ยท 2026

The quality of training data is critical to the performance of machine learning models. In this paper, the Error Sensitivity Profile (ESP) is proposed. It quantifies the sensitivity of model performanโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Threat-Oriented Digital Twinning for Security Evaluation of Autonomous Platforms

Thomas J. Neubert, Laxima Niure Kandel, Berker Pekoz ยท 2026

Open, unclassified research on secure autonomy is constrained by limited access to operational platforms, contested communications infrastructure, and representative adversarial test conditions. This โ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Predicting challenging phase transitions with Bayesian active learning

Lorenzo Bastonero, Gabriel Joalland, Chiara Cignarella, Lorenzo Monacelli, Nicola Marzari ยท 2026

Materials underpin modern technologies, from energy harvesting, storage, and conversion to information and communication technologies. Their functionality is often governed by the interplay between coโ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Quantum-Inspired Robust and Scalable SAR Object Classification

Maximilian Scharf, Marco Trenti, Felix Bock, Padraig Davidson, Tobias Brosch, Benjamin Rodrigues de Miranda, Sigurd Huber, Timo Felser ยท 2026

SAR image classification naturally has to deal with huge noise and a high dynamic range particularly requiring robust classification models. Additionally, the deployment of these models on edge deviceโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Bayesian Environment Invariant Regression

Ruqian Zhang, Juan Shen, Yijiao Zhang ยท 2026

The availability of data from multiple heterogeneous environments has motivated methods that remain reliable under distributional shifts. When the joint distribution of response and predictors varies โ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

QAROO: AI-Driven Online Task Offloading for Energy-Efficient and Sustainable MEC Networks

Yongtao Yao, Yao Yang, Haorui Shi, Canglu Zhu, Miaojiang Chen, Ahmed Farouk ยท 2026

With the rapid advancement of artificial intelligence (AI) and intelligent science, intelligent edge computing has been widely adopted. However, the limitations of traditional methods, such as poor adโ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Characterisation of the Clouds' young stellar Bridge using Gaia DR3

Marie Scholch, Oscar Jimenez-Arranz, Merce Romero-Gomez, Xavier Luri ยท 2026

The interaction between the LMC and SMC (the Clouds) has resulted in prominent tidal features, including an extended bridge of gas and stars connecting the two galaxies. This Bridge has likely formed โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users

Xiaodong Li, Jiawei Sheng, Jiangxia Cao, Xinghua Zhang, Wenyuan Zhang, Yong Sun, Shirui Pan, Zhihong Tian, Tingwen Liu ยท 2026

Cross-domain recommendation (CDR) has demonstrated to be an effective solution for alleviating the user cold-start issue. By leveraging rich user-item interactions available in a richly informative soโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Joint Design of Doppler-Resilient Unimodular Discrete-Phase Waveforms and Receiving Filters for MIMO Radars

Junpeng Ma, Yuke Li, Junbo Wang, Yongxing Zhou ยท 2026

Designing Doppler-resilient unimodular discrete phase-coded waveforms (DPWs) with low delay-Doppler sidelobes is critical for multiple-input multiple-output (MIMO) radar. Existing block coordinate desโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Designing and Evaluating Next-Generation Learning Interfaces: Linking AI, HCI, and the Learning Sciences

Meng Xia, Yan Chen, Qiao Jin, Yang Shi, Paul Denny, Tiffany Barnes, Qingsong Wen, Vincent Aleven ยท 2026

This workshop addresses this gap by bringing together researchers and practitioners from AI, HCI, and the learning sciences to explore how interactive systems can better support learning. We focus on โ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Toward Multimodal Conversational AI for Age-Related Macular Degeneration

Ran Gu, Benjamin Hou, Melanie Hebert, Asmita Indurkar, Yifan Yang, Emily Y. Chew, Tiarnan D. L. Keenan, Zhiyong Lu ยท 2026

Despite strong performance of deep learning models in retinal disease detection, most systems produce static predictions without clinical reasoning or interactive explanation. Recent advances in multiโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Step-Audio-R1.5 Technical Report

Yuxin Zhang, Xiangyu Tony Zhang, Daijiao Liu, Fei Tian, Yayue Deng, Jun Chen, Qingjian Lin, Haoyang Zhang, Yuxin Li, Jinglan Gong, Yechang Huang, Liang Zhao, Chengyuan Yao, Hexin Liu, Eng Siong Chng, Xuerui Yang, Gang Yu, Xiangyu Zhang, Daxin Jiang ยท 2026

Recent advancements in large audio language models have extended Chain-of-Thought (CoT) reasoning into the auditory domain, enabling models to tackle increasingly complex acoustic and spoken tasks. Toโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Learning Generalizable Multimodal Representations for Software Vulnerability Detection

Zeming Dong, Yuejun Guo, Qiang Hu, Yao Zhang, Maxime Cordy, Hao Liu, Mike Papadakis, Yongqiang Lyu ยท 2026

Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capture developer intent. However, existing vulnerability deteโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Adaptive Meta-Learning Stochastic Gradient Hamiltonian Monte Carlo Simulation for Bayesian Updating of Structural Dynamic Models

Xianghao Meng, James L. Beck, Yong Huang, Hui Li ยท 2026

In the last few decades, Markov chain Monte Carlo (MCMC) methods have been widely applied to Bayesian updating of structural dynamic models in the field of structural health monitoring. Recently, seveโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Backtranslation Augmented Direct Preference Optimization for Neural Machine Translation

Mehrdad Ghassabi, Spehr Rajabi, Hamidreza Baradaran Kashani, Sadra Hakim, Mahshid Keivandarian ยท 2026

Contemporary neural machine translation (NMT) systems are almost exclusively built by training on supervised parallel data. Despite the tremendous progress achieved, these systems still exhibit persisโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Bug-Report-Driven Fault Localization: Industrial Benchmarking and Lesson Learned at ABB Robotics

Pernilla Hall, Anton Ununger, Riccardo Rubei, Alessio Bucaioni ยท 2026

Software quality assurance remains a major challenge in industrial environments, where large-scale and long-lived systems inevitably accumulate defects. Identifying the location of a fault is often tiโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Reference-Augmented Learning for Precise Tracking Policy of Tendon-Driven Continuum Robots

Ziqing Zou, Ke Qiu, Haojian Lu, Rong Xiong, Yue Wang ยท 2026

Tendon-Driven Continuum Robots (TDCRs) pose significant control challenges due to their highly nonlinear, path-dependent dynamics and non-Markovian characteristics. Traditional Jacobian-based controllโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Learning-Based Dynamics Modeling and Robust Control for Tendon-Driven Continuum Robots

Ziqing Zou, Ke Qiu, Fei Wang, Haojian Lu, Rong Xiong, Yue Wang ยท 2026

Tendon-Driven Continuum Robots (TDCRs) pose significant modeling and control challenges due to complex nonlinearities, such as frictional hysteresis and transmission compliance. This paper proposes a โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance

Chen Yifei, Tian Zhixing, Wang Chenyang, Cheng Ziguang ยท 2026

This paper targets e-commerce search relevance. While Large Language Models (LLMs) have demonstrated significant potential in this field, they often encounter performance bottlenecks in persistent 'coโ€ฆ

Read Paper โ†’
โ† Prev Page 20 of 17334 Next โ†’