Related papers: DAS: Dual-Aligned Semantic IDs Empowered Industria…

In this paper, we study data-aided sensing (DAS) for a system consisting of a base station (BS) and a number of nodes, where the BS becomes a receiver that collects measurements or data sets from the nodes that are distributed over a cell.…

Display advertising provides significant value to advertisers, publishers, and users. Traditional display advertising systems utilize a multi-stage architecture consisting of retrieval, coarse ranking, and final ranking. However,…

Learning segmentation from synthetic data and adapting to real data can significantly relieve human efforts in labelling pixel-level masks. A key challenge of this task is how to alleviate the data distribution discrepancy between the…

Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discretize this information into compact tokens. However, two challenges persist: (1) Suboptimal…

Successive proposals of several self-supervised training schemes continue to emerge, taking one step closer to developing a universal foundation model. In this process, the unsupervised downstream tasks are recognized as one of the…

Multimodal recommendation systems have attracted increasing attention for their improved performance by leveraging items' multimodal information. Prior methods often build modality-specific item-item semantic graphs from raw modality…

Beam alignment is essential to compensate for the high path loss in the millimeter-wave (mmWave) Unmanned Aerial Vehicle (UAV) network. The integrated sensing and communication (ISAC) technology has been envisioned as a promising solution…

Despite the achievements of large-scale multimodal pre-training approaches, cross-modal retrieval, e.g., image-text retrieval, remains a challenging task. To bridge the semantic gap between the two modalities, previous studies mainly focus…

Semi-supervised learning has proven highly effective in tackling the challenge of limited labeled training data in medical image segmentation. In general, current approaches, which rely on intra-image pixel-wise consistency training via…

While self-training has advanced semi-supervised semantic segmentation, it severely suffers from the long-tailed class distribution on real-world semantic segmentation datasets that make the pseudo-labeled data bias toward majority classes.…

Cross-domain recommendation (CDR) is crucial for improving recommendation accuracy and generalization, yet traditional methods are often hindered by the reliance on shared user/item IDs, which are unavailable in most real-world scenarios.…

Sentiment analysis plays a crucial role in various domains, such as business intelligence and financial forecasting. Large language models (LLMs) have become a popular paradigm for sentiment analysis, leveraging multi-task learning to…

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…

Recently, deep self-training approaches emerged as a powerful solution to the unsupervised domain adaptation. The self-training scheme involves iterative processing of target data; it generates target pseudo labels and retrains the network.…

Recently, semi-supervised semantic segmentation has achieved promising performance with a small fraction of labeled data. However, most existing studies treat all unlabeled data equally and barely consider the differences and training…

This paper introduces SOLID (Synergizing Optimization and Large Language Models for Intelligent Decision-Making), a novel framework that integrates mathematical optimization with the contextual capabilities of large language models (LLMs).…

Non-English dialogue datasets are scarce, and models are often trained or evaluated on translations of English-language dialogues, an approach which can introduce artifacts that reduce their naturalness and cultural appropriateness. This…

Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes. This imbalance degrades the performance of typical…

Semantic parsing aims to transform natural language (NL) utterances into formal meaning representations (MRs), whereas an NL generator achieves the reverse: producing a NL description for some given MRs. Despite this intrinsic connection,…

LiDAR semantic segmentation provides 3D semantic information about the environment, an essential cue for intelligent systems during their decision making processes. Deep neural networks are achieving state-of-the-art results on large public…