Expertini Research Research

Browse Research Papers

346,661+ open-access research outputs.

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

From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space

Pengyue Jia, Xiaobei Wang, Yingyi Zhang, Shuchang Liu, Yupeng Hou, Hailan Yang, Xu Gao, Xiaopeng Li, Yejing Wang, Julian McAuley, Xiang Li, Lantao Hu, Yongqi Liu, Kaiqiao Zhan, Han Li, Kun Gai, Xiangyu Zhao ยท 2026

In modern recommender systems, list-wise reranking serves as a critical phase within the multi-stage pipeline, finalizing the exposed item sequence and directly impacting user satisfaction by modelingโ€ฆ

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

OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding

Minghang Zheng, Zihao Yin, Yi Yang, Yuxin Peng, Yang Liu ยท 2026

Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps โ€ฆ

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

Combating Visual Neglect and Semantic Drift in Large Multimodal Models for Enhanced Cross-Modal Retrieval

Guosheng Zhang, Linkai Liu, Keyao Wang, Haixiao Yue, Zhiwen Tan, Xiao Tan ยท 2026

Despite significant progress in Unified Multimodal Retrieval (UMR) powered by Large Multimodal Models (LMMs), existing embedding methods primarily focus on sample-level objectives via contrastive learโ€ฆ

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

Spectral bandits

Tomas Kocak, Remi Munos, Branislav Kveton, Shipra Agrawal, Michal Valko ยท 2026

Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this work, we study a bandit problem where the payoffs of arms are smooth on a graph. This framework is sโ€ฆ

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

Online learning with Erd\H{o}s-R\'enyi side-observation graphs

Tomas Kocak, Gergely Neu, Michal Valko ยท 2026

We consider adversarial multi-armed bandit problems where the learner is allowed to observe losses of a number of arms beside the arm that it actually chose. We study the case where all non-chosen armโ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Integrand Analysis, Leading Singularities and Canonical Bases beyond Polylogarithms

Felix Forner, Cesare Carlo Mella, Christoph Nega, Lorenzo Tancredi, Fabian J. Wagner ยท 2026

In this paper, we elaborate on the connection between leading singularities and canonical bases of Feynman integrals beyond polylogarithms. We start by discussing a notion of leading singularities in โ€ฆ

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

Online combinatorial optimization with stochastic decision sets and adversarial losses

Gergely Neu, Michal Valko ยท 2026

Most work on sequential learning assumes a fixed set of actions that are available all the time. However, in practice, actions can consist of picking subsets of readings from sensors that may break frโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

MARD: A Multi-Agent Framework for Robust Android Malware Detection

Xueying Zeng, Youquan Xian, Sihao Liu, Xudong Mou, Yanze Li, Lei Cui, Bo Li ยท 2026

With the rapid evolution of Android applications, traditional machine learning-based detection models suffer from concept drift. Additionally, they are constrained by shallow features, lacking deep seโ€ฆ

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

DGLight: DQN-Guided GRPO Fine-Tuning of Large Language Models for Traffic Signal Control

Chenbo Yu ยท 2026

Traffic signal control (TSC) plays a central role in reducing congestion and maintaining urban mobility. This dissertation introduces DGLight, a critic-guided reinforcement-learning framework for adapโ€ฆ

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

Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation

Tianshui Chen, Yujie Zhu, Jianman Lin, Zhijing Yang, Chunmei Qing, Feng Gao, Liang Lin ยท 2026

Speech-preserving facial expression manipulation (SPFEM) aims to enhance human expressiveness without altering mouth movements tied to the original speech. A primary challenge in this domain is the scโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Digital Twin-assisted belief-state reinforcement learning for latency-robust ISAC in 6G networks

Himanshu Tiwari, Binayak Kar, Priyanshu Tiwari ยท 2026

Integrated Sensing and Communication (ISAC) enables joint data transmission and environmental perception for sixth-generation (6G) networks, but centralized and virtualized RAN control loops introduceโ€ฆ

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

Below-Chance Blindness: Prompted Underperformance in Small LLMs Produces Positional Bias Rather than Answer Avoidance

Jon-Paul Cacioli ยท 2026

Detecting sandbagging--the deliberate underperformance on capability evaluations--is an open problem in AI safety. We tested whether symptom validity testing (SVT) logic from clinical malingering deteโ€ฆ

Read Paper โ†’
Biology & Life Sciences Preprint PDF DOI

Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics

Haocheng Tang, Liang Shi, Ya-Shi Zhang, Xixian Liu, Jian Tang, Jiarui Lu ยท 2026

Protein dynamics underlie many biological functions, yet remain difficult to characterize due to the high computational cost of molecular dynamics simulations and the scarcity of dynamic structural daโ€ฆ

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

Categorical Optimization with Bayesian Anchored Latent Trust Regions for Structural Design under High-Dimensional Uncertainty

Zhangyong Liang, Huanhuan Gao ยท 2026

Categorical structural optimization under aleatoric uncertainty is challenging because each design variable must be selected from a finite catalog of admissible instances, while each candidate design โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Adaptive Management of Microservices in Dynamic Computing Environments: A Taxonomy and Future Directions

Ming Chen, Muhammed Tawfiqul Islam, Maria Rodriguez Read, Rajkumar Buyya ยท 2026

Microservice-based cloud applications face changing workloads, evolving request paths, variable network conditions, interference, and failures. These dynamics couple autoscaling, placement, routing, iโ€ฆ

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

Adversarial Robustness of NTK Neural Networks

Yuxuan Hou ยท 2026

Deep learning models are widely deployed in safety-critical domains, but remain vulnerable to adversarial attacks. In this paper, we study the adversarial robustness of NTK neural networks in the contโ€ฆ

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

Towards Seamless Lunar Mosaics: Deep Radiometric Normalization for Cross-Sensor Orbital Imagery Using Chandrayaan-2 TMC Data

Pratincha Singh, Jai Gopal Singla, Prashant Hemrajani, Nitant Dube, Amithabh, Hinal Patel ยท 2026

Radiometric inconsistencies remain a major challenge in generating seamless lunar mosaics from multi-mission orbital imagery due to variability in illumination geometry, sensor characteristics, and acโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Making AI-Assisted Grant Evaluation Auditable without Exposing the Model

Kemal Bicakci ยท 2026

Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical governance problem: the model and scoring rubric should โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Optimization of Model Splitting, Placement, and Chaining for Multi-hop Split Learning and Inference

Takanori Hara, Masahiro Sasabe ยท 2026

Service Function Chaining (SFC) establishes efficient communication paths by ensuring that traffic traverses a predefined sequence of network functions in a specified order to meet particular service โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

How Can Reinforcement Learning Achieve Expert-level Placement?

Ruo-Tong Chen, Ke Xue, Chengrui Gao, Yunqi Shi, Tian Xu, Peng Xie, Siyuan Xu, Mingxuan Yuan, Chao Qian, Zhi-Hua Zhou ยท 2026

Chip placement is a critical step in physical design. While reinforcement learning (RL)-based methods have recently emerged, their training primarily focuses on wirelength optimization, and therefore โ€ฆ

Read Paper โ†’
โ† Prev Page 24 of 17334 Next โ†’