346,661+ open-access research outputs.
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 modelingโฆ
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 โฆ
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 learโฆ
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 sโฆ
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 armโฆ
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 โฆ
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 frโฆ
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 seโฆ
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 adapโฆ
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 scโฆ
Integrated Sensing and Communication (ISAC) enables joint data transmission and environmental perception for sixth-generation (6G) networks, but centralized and virtualized RAN control loops introduceโฆ
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 deteโฆ
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 daโฆ
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 โฆ
Microservice-based cloud applications face changing workloads, evolving request paths, variable network conditions, interference, and failures. These dynamics couple autoscaling, placement, routing, iโฆ
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 contโฆ
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 acโฆ
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 โฆ
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 โฆ
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 โฆ
Free open-access publishing with Google Scholar indexing.
Submission Guide โ