Magnitude-based Neuron Pruning for Backdoor Defens: Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research... arxiv.org/abs/2405.17750
ORLM: Training Large Language Models for Optimization Modeling: Large Language Models (LLMs) have emerged as powerful tools for tackling complex Operations Research (OR) problem by providing the capacity in auto... arxiv.org/abs/2405.17743
Ai.llude: Encouraging Rewriting AI-Generated Text to Support Creative Expression: In each step of the creative writing process, writers must grapple with their creative goals and individual perspectives. This process affects the ... arxiv.org/abs/2405.17843
On the Sequence Evaluation based on Stochastic Processes: Modeling and analyzing long sequences of text is an essential task for Natural Language Processing. Success in capturing long text dynamics using n... arxiv.org/abs/2405.17764
Mollification Effects of Policy Gradient Methods: Policy gradient methods have enabled deep reinforcement learning (RL) to approach challenging continuous control problems, even when the underlying... arxiv.org/abs/2405.17832
Unmasking Vulnerabilities: Cardinality Sketches under Adaptive Inputs: Cardinality sketches are popular data structures that enhance the efficiency of working with large data sets. The sketches are randomized represent... arxiv.org/abs/2405.17780
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective: Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research... arxiv.org/abs/2405.17746
The Widening Gap: The Benefits and Harms of Generative AI for Novice Programmers: Novice programmers often struggle through programming problem solving due to a lack of metacognitive awareness and strategies. Previous research ha... arxiv.org/abs/2405.17739
Benchmark Underestimates the Readiness of Multi-lingual Dialogue Agents: Creating multilingual task-oriented dialogue (TOD) agents is challenging due to the high cost of training data acquisition. Following the research ... arxiv.org/abs/2405.17840
DanceGen: Supporting Choreography Ideation and Prototyping with Generative AI: Choreography creation requires high proficiency in artistic and technical skills. Choreographers typically go through four stages to create a dance... arxiv.org/abs/2405.17827
Revisiting the Message Passing in Heterophilous Graph Neural Networks: Graph Neural Networks (GNNs) have demonstrated strong performance in graph mining tasks due to their message-passing mechanism, which is aligned wi... arxiv.org/abs/2405.17768
SLMRec: Empowering Small Language Models for Sequential Recommendation: The sequential Recommendation (SR) task involves predicting the next item a user is likely to interact with, given their past interactions. The SR ... arxiv.org/abs/2405.17890
AI Alignment with Changing and Influenceable Reward Functions: Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by ou... arxiv.org/abs/2405.17713
Diffusion Model Patching via Mixture-of-Prompts: We present Diffusion Model Patching (DMP), a simple method to boost the performance of pre-trained diffusion models that have already reached conve... arxiv.org/abs/2405.17825
Dataset Regeneration for Sequential Recommendation: The sequential recommender (SR) system is a crucial component of modern recommender systems, as it aims to capture the evolving preferences of user... arxiv.org/abs/2405.17795
On the Downlink Average {Energy }Efficiency of Non-Stationary XL-MIMO: Extra large-scale multiple-input multiple-output (XL-MIMO) is a key technology for future wireless communication systems. This paper considers the ... arxiv.org/abs/2405.17789
Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation: In this study, we aim to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generativ... arxiv.org/abs/2405.17842
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment: Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being s... arxiv.org/abs/2405.17871
Bandwidth Efficient Cache Selection and Content Advertisement: Caching is extensively used in various networking environments to optimize performance by reducing latency, bandwidth, and energy consumption. To o... arxiv.org/abs/2405.17801