Related papers: Towards Efficient and Generalizable Retrieval: Ada…

Sequential recommendation aims to recommend the next item of users' interest based on their historical interactions. Recently, the self-attention mechanism has been adapted for sequential recommendation, and demonstrated state-of-the-art…

Current learning-based Automated Vulnerability Repair (AVR) approaches, while promising, often fail to generalize effectively in real-world scenarios. Our diagnostic analysis reveals three fundamental weaknesses in state-of-the-art AVR…

Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from queries. While this model-as-index paradigm offers architectural simplicity, it is poorly…

Efficient question-answering (QA) over extensive scientific literature is essential for evidence-based engineering decision-making. Retrieval-augmented generation (RAG) is increasingly applied to question-answering over long academic…

Casting session-based or sequential recommendation as reinforcement learning (RL) through reward signals is a promising research direction towards recommender systems (RS) that maximize cumulative profits. However, the direct use of RL…

Conversion objectives in large-scale recommender systems are sparse, making them difficult to optimize. Generative recommendation (GR) partially alleviates data sparsity by organizing multi-type behaviors into a unified token sequence with…

Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data…

Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural…

Recently, there have been significant advances in neural methods for tackling knowledge-intensive tasks such as open domain question answering (QA). These advances are fueled by combining large pre-trained language models with learnable…

Unlike conventional person re-identification (ReID), clothes-changing ReID (CC-ReID) presents severe challenges due to substantial appearance variations introduced by clothing changes. In this work, we propose the Quality-Aware Dual-Branch…

Recently, the generality of natural language text has been leveraged to develop transferable recommender systems. The basic idea is to employ pre-trained language models~(PLM) to encode item text into item representations. Despite the…

Any-Time Person Re-identification (AT-ReID) necessitates the robust retrieval of target individuals under arbitrary conditions, encompassing both modality shifts (daytime and nighttime) and extensive clothing-change scenarios, ranging from…

Although prevailing supervised and self-supervised learning augmented sequential recommendation (SeRec) models have achieved improved performance with powerful neural network architectures, we argue that they still suffer from two…

Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual query tokens directly to image patches and achieving state-of-the-art performance on public benchmarks. Recent models relying on this paradigm…

Semi-supervised domain adaptation (SSDA) has been extensively researched due to its ability to improve classification performance and generalization ability of models by using a small amount of labeled data on the target domain. However,…

Under limited data setting, GANs often struggle to navigate and effectively exploit the input latent space. Consequently, images generated from adjacent variables in a sparse input latent space may exhibit significant discrepancies in…

Scene Graph Generation (SGG) research has suffered from two fundamental challenges: the long-tailed predicate distribution and semantic ambiguity between predicates. These challenges lead to a bias towards head predicates in SGG models,…

Traditional sparse and dense retrieval methods struggle to leverage general world knowledge and often fail to capture the nuanced features of queries and products. With the advent of large language models (LLMs), industrial search systems…

Acoustic Scene Classification (ASC) faces challenges in generalizing across recording devices, particularly when labeled data is limited. The DCASE 2024 Challenge Task 1 highlights this issue by requiring models to learn from small labeled…

Embedding-based retrieval serves as a dominant approach to candidate item matching for industrial recommender systems. With the success of generative AI, generative retrieval has recently emerged as a new retrieval paradigm for…