Related papers: SIDE: Semantic ID Embedding for effective learning…

Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often…

Given the effectiveness and ease of use, Item-based Collaborative Filtering (ICF) methods have been broadly used in industry in recent years. The key of ICF lies in the similarity measurement between items, which however is a coarse-grained…

User and item cold starts present significant challenges in industrial applications of recommendation systems. Supplementing user-item interaction data with metadata is a common solution-but often at the cost of introducing additional…

Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems. Traditional approaches, often separating the two steps of embedding learning and…

Pretrained contextualized embeddings are powerful word representations for structured prediction tasks. Recent work found that better word representations can be obtained by concatenating different types of embeddings. However, the…

We propose SemCSE-Multi, a novel unsupervised framework for generating multifaceted embeddings of scientific abstracts, evaluated in the domains of invasion biology and medicine. These embeddings capture distinct, individually specifiable…

Semi-supervised domain adaptation (SSDA) presents a critical hurdle in computer vision, especially given the frequent scarcity of labeled data in real-world settings. This scarcity often causes foundation models, trained on extensive…

Computer vision (CV) datasets often exhibit biases that are perpetuated by deep learning models. While recent efforts aim to mitigate these biases and foster fair representations, they fail in complex real-world scenarios. In particular,…

Entity disambiguation (ED) is the task of linking mentions in text to corresponding entries in a knowledge base. Dual Encoders address this by embedding mentions and label candidates in a shared embedding space and applying a similarity…

Learned embeddings for products are an important building block for web-scale e-commerce recommendation systems. At Pinterest, we build a single set of product embeddings called ItemSage to provide relevant recommendations in all shopping…

This article identifies and addresses a fundamental bottleneck in data-driven 360-degree image quality assessment (IQA): the lack of intelligent, sample-level data selection. Hence, we propose a novel framework that introduces a critical…

Semantic caching enhances the efficiency of large language model (LLM) systems by identifying semantically similar queries, storing responses once, and serving them for subsequent equivalent requests. However, existing semantic caching…

Visualization recommendation systems simplify exploratory data analysis (EDA) and make understanding data more accessible to users of all skill levels by automatically generating visualizations for users to explore. However, most existing…

Product Quantization (PQ) construction is deeply integrated into vector index construction for Approximate Nearest Neighbor Search (ANNS). The rapid growth in vector dimensionality and volume has significantly increased the computational…

A key characteristic of deep recommendation models is the immense memory requirements of their embedding tables. These embedding tables can often reach hundreds of gigabytes which increases hardware requirements and training cost. A common…

Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong generalization, their direct image-text embedding alignment…

Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object recognition. SED…

The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules, relying on auxiliary index…

Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of…

While most frontier models still use deterministic frequency-based tokenization algorithms such as byte-pair encoding (BPE), there has been significant recent work to design learned neural tokenizers. However, these schemes generally add to…