Related papers: Towards Efficient and Generalizable Retrieval: Ada…
Foundation models in language and vision benefit from a unified discrete token interface that converts raw inputs into sequences for scalable pre-training and inference. For graphs, an effective tokenizer should yield reusable discrete…
Accurate annotation of educational resources is crucial for effective personalized learning and resource recommendation in online education. However, fine-grained knowledge labels often overlap or share similarities, making it difficult for…
The paper addresses challenges in storing and retrieving sequences in contexts like anomaly detection, behavior prediction, and genetic information analysis. Associative Knowledge Graphs (AKGs) offer a promising approach by leveraging…
Generative recommendation (GR) has gained increasing attention for its promising performance compared to traditional models. A key factor contributing to the success of GR is the semantic ID (SID), which converts continuous semantic…
Autoregressive models have emerged as a powerful paradigm for visual content creation, but often overlook the intrinsic structural properties of visual data. Our prior work, IAR, initiated a direction to address this by reorganizing the…
Generalized Category Discovery (GCD) aims to identify both known and unknown categories, with only partial labels given for the known categories, posing a challenging open-set recognition problem. State-of-the-art approaches for GCD task…
Text-to-Video Retrieval (TVR) is essential in video platforms. Dense retrieval with dual-modality encoders leads in accuracy, but its computation and storage scale poorly with corpus size. Thus, real-time large-scale applications adopt…
Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution.…
This paper presents CRACQ, a multi-dimensional evaluation framework tailored to evaluate documents across f i v e specific traits: Coherence, Rigor, Appropriateness, Completeness, and Quality. Building on insights from traitbased Automated…
Conventional Sequential Recommender Systems (SRS) typically assign unique hash IDs (HID) to construct item embeddings, which mainly capture collaborative signals from historical user-item interactions. However, such embeddings are…
Sequential recommendation systems often struggle to make predictions or take action when dealing with cold-start items that have limited amount of interactions. In this work, we propose SimRec - a new approach to mitigate the cold-start…
The discovery of environmental knowledge depends on labeled task-specific data, but is often constrained by the high cost of data collection. Existing machine learning approaches usually struggle to generalize in data-sparse or atypical…
Text-to-image diffusion models have achieved remarkable progress in generating diverse and realistic images from textual descriptions. However, they still struggle with personalization, which requires adapting a pretrained model to depict…
Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR…
The ability to efficiently search for images is essential for improving the user experiences across various products. Incorporating user feedback, via multi-modal inputs, to navigate visual search can help tailor retrieved results to…
In multimodal multi-hop question answering, we focus on the initial retrieval stage via two distinct tasks: (1) evidence set completion, retrieving missing evidence given context, and (2) sequential pool construction, iteratively building…
Generative retrieval with Semantic IDs (SIDs) assigns each item a discrete identifier and treats retrieval as a sequence generation problem rather than a nearest-neighbor search. While content-only SIDs are stable, they do not take into…
Generative retrieval (Wang et al., 2022; Tay et al., 2022) is a popular approach for end-to-end document retrieval that directly generates document identifiers given an input query. We introduce summarization-based document IDs, in which…
Sequence-based recommendations models are driving the state-of-the-art for industrial ad-recommendation systems. Such systems typically deal with user histories or sequence lengths ranging in the order of O(10^3) to O(10^4) events. While…
Generative Large Language Models enable efficient analytics across knowledge domains, rivalling human experts in information comparisons. However, the applications of LLMs for information comparisons face scalability challenges due to the…