Related papers: Learning Large-scale Universal User Representation…

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…

Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE models have focused primarily on coarse-grained MoE…

Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks,…

Continual fine-tuning of large language models (LLMs) suffers from catastrophic forgetting. Rehearsal-based methods mitigate this problem by retaining a small set of old data. Nevertheless, they still suffer inevitable performance loss.…

Leveraging Large Language Models (LLMs) for recommendation has demonstrated notable success in various domains, showcasing their potential for open-domain recommendation. A key challenge to advancing open-domain recommendation lies in…

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language models to infer user preferences, but the derived prompts or…

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific levels of linguistic units. This work introduces universal language representation learning, i.e.,…

Sparse Mixture of Experts (SMoEs) models scale the capacity of models while maintaining constant computational overhead. Early designs typically relied on a fixed value of $k$, where $k$ represents either the number of experts selected per…

Multimodal federated learning in real-world settings often encounters incomplete and heterogeneous data across clients. This results in misaligned local feature representations that limit the effectiveness of model aggregation. Unlike prior…

Supervised machine-learning models often underperform in predicting user behaviors from conversational text, hindered by poor crowdsourced label quality and low NLP task accuracy. We introduce the Metadata-Sensitive Weighted-Encoding…

Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost of training and evaluating models. Efficient Pareto front…

Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domains, or by introducing unlabeled target variation data to…

E-commerce platforms generate vast amounts of customer behavior data, such as clicks and purchases, from millions of unique users every day. However, effectively using this data for behavior understanding tasks is challenging because there…

Dense Retrieval Models (DRMs) are a prominent development in Information Retrieval (IR). A key challenge with these neural Transformer-based models is that they often struggle to generalize beyond the specific tasks and domains they were…

To build an artificial neural network like the biological intelligence system, recent works have unified numerous tasks into a generalist model, which can process various tasks with shared parameters and do not have any task-specific…

Inductive transfer learning has had a big impact on computer vision and NLP domains but has not been used in the area of recommender systems. Even though there has been a large body of research on generating recommendations based on…

Sequential recommendation has rapidly advanced in click-through rate prediction due to its ability to model dynamic user interests. A key challenge, however, lies in modeling long sequences: users often exhibit significant interest shifts,…

An unsupervised human action modeling framework can provide useful pose-sequence representation, which can be utilized in a variety of pose analysis applications. In this work we propose a novel temporal pose-sequence modeling framework,…

Machine learning models often need to adapt to new data after deployment due to structured or unstructured real-world dynamics. The Continual Learning (CL) framework enables continuous model adaptation, but most existing approaches either…