Related papers: Diffusion-Inspired Cold Start with Sufficient Prio…
Previous knowledge distillation methods have shown their impressive performance on model compression tasks, however, it is hard to explain how the knowledge they transferred helps to improve the performance of the student network. In this…
Self-supervised learning (SSL) in the pretraining stage using un-annotated speech data has been successful in low-resource automatic speech recognition (ASR) tasks. However, models trained through SSL are biased to the pretraining data…
Cross-Domain Recommendation (CDR) is a promising paradigm inspired by transfer learning to solve the cold-start problem in recommender systems. Existing state-of-the-art CDR methods train an explicit mapping function to transfer the…
Domain Generalization (DG) seeks to transfer knowledge from multiple source domains to unseen target domains, even in the presence of domain shifts. Achieving effective generalization typically requires a large and diverse set of labeled…
Recent advances in powerful pre-trained diffusion models encourage the development of methods to improve the sampling performance under well-trained diffusion models. This paper introduces Diffusion Rejection Sampling (DiffRS), which uses a…
Reusing pre-collected data from different domains is an appealing solution for decision-making tasks, especially when data in the target domain are limited. Existing cross-domain policy transfer methods mostly aim at learning domain…
Recommender systems are widely used in various real-world applications, but they often encounter the persistent challenge of the user cold-start problem. Cross-domain recommendation (CDR), which leverages user interactions from one domain…
Collaborative filtering (CF) aims to predict users' ratings on items according to historical user-item preference data. In many real-world applications, preference data are usually sparse, which would make models overfit and fail to give…
In this work, we present a domain-independent approach for adaptive scaffolding in robotic explanation generation to guide tasks in human-robot interaction. We present a method for incorporating interdisciplinary research results into a…
Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong…
Few-Shot Class-Incremental Learning (FSCIL) challenges models to sequentially learn new classes from minimal examples without forgetting prior knowledge, a task complicated by the stability-plasticity dilemma and data scarcity. Current…
Online test-time adaptation aims to dynamically adjust a network model in real-time based on sequential input samples during the inference stage. In this work, we find that, when applying a transformer network model to a new target domain,…
Recent advances in diffusion models show promising potential to accelerate nonconvex problem solving by leveraging their multimodality. However, most existing diffusion-based optimization approaches rely on supervised learning and lack a…
Continual Test-Time Adaptation (CTTA) aims to quickly fine-tune the model during the test phase so that it can adapt to multiple unknown downstream domain distributions without pre-acquiring downstream domain data. To this end, existing…
Diffusion models have demonstrated remarkable capabilities in generating high-quality samples and enhancing performance across diverse domains through Classifier-Free Guidance (CFG). However, the quality of generated samples is highly…
Object detectors often suffer a decrease in performance due to the large domain gap between the training data (source domain) and real-world data (target domain). Diffusion-based generative models have shown remarkable abilities in…
A recent study has shown that diffusion models are well-suited for modeling the generative process of user-item interactions in recommender systems due to their denoising nature. However, existing diffusion model-based recommender systems…
Recent advancements in diffusion models have shown promising results in sequential recommendation (SR). Existing approaches predominantly rely on implicit conditional diffusion models, which compress user behaviors into a single…
Predicting Click-Through Rates is a crucial function within recommendation and advertising platforms, as the output of CTR prediction determines the order of items shown to users. The Embedding \& MLP paradigm has become a standard approach…
Deep learning models are widely used for time series classification (TSC) due to their scalability and efficiency. However, their performance degrades under challenging data conditions such as class similarity, multimodal distributions, and…