Related papers: How Reliable Are Semantic-ID Tokenizer Comparisons…
With the rise of modern search and recommendation platforms, insufficient collaborative information of cold-start items exacerbates the Matthew effect of existing platform items, challenging platform diversity and becoming a longstanding…
We present SEED (Semantic Evaluation for Visual Brain Decoding), a novel metric for evaluating the semantic decoding performance of visual brain decoding models. It integrates three complementary metrics, each capturing a different aspect…
Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally semantically misaligned due to the diversity of human poses and…
Generative recommendation models often struggle with two key challenges: (1) the superficial integration of collaborative signals, and (2) the decoupled fusion of multimodal features. These limitations hinder the creation of a truly…
Sequential Recommender Systems (SRSs) are a popular type of recommender system that learns from a user's history to predict the next item they are likely to interact with. However, user interactions can be affected by noise stemming from…
At the present time, sequential item recommendation models are compared by calculating metrics on a small item subset (target set) to speed up computation. The target set contains the relevant item and a set of negative items that are…
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…
Sequential recommendation aims to predict the next item based on user interests in historical interaction sequences. Historical interaction sequences often contain irrelevant noisy items, which significantly hinders the performance of…
Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three…
The recent success of large language models (LLMs) has renewed interest in whether recommender systems can achieve similar scaling benefits. Conventional recommenders, dominated by massive embedding tables, tend to plateau as embedding…
Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval process into a single end-to-end model. However, its practical adoption in industrial e-commerce search remains challenging, given the…
Sequential recommendation demonstrates the capability to recommend items by modeling the sequential behavior of users. Traditional methods typically treat users as sequences of items, overlooking the collaborative relationships among them.…
Computer-Aided Design (CAD) is a foundational component of industrial prototyping, where models are defined not by raw coordinates but by construction sequences such as sketches and extrusions. This sequential structure enables both…
Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text,…
Generative recommendation models sequence generation to produce items end-to-end, but training from behavioral logs often provides weak supervision on underlying user intent. Although Large Language Models (LLMs) offer rich semantic priors…
Software-related platforms have enabled their users to collaboratively label software entities with topics. Tagging software repositories with relevant topics can be exploited for facilitating various downstream tasks. For instance, a…
Traditional sequential recommendation (SR) methods heavily rely on explicit item IDs to capture user preferences over time. This reliance introduces critical limitations in cold-start scenarios and domain transfer tasks, where unseen items…
Tokenization is a fundamental technique in the generative modeling of various modalities. In particular, it plays a critical role in autoregressive (AR) models, which have recently emerged as a compelling option for 3D generation. However,…
Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single sequence-to-sequence model is learned to directly generate a list of relevant document identifiers (docids) given a query. Existing GR models commonly…
Recent generative models produce near-photorealistic images, challenging the trustworthiness of photographs. Synthetic image detection (SID) has thus become an important area of research. Prior work has highlighted how synthetic images…