Related papers: Pre-training Contextual Location Embeddings in Per…

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,…

In recent years, there has been a rapid development of spatio-temporal prediction techniques in response to the increasing demands of traffic management and travel planning. While advanced end-to-end models have achieved notable success in…

Foundation models for structured electronic health records (EHRs) are pretrained on longitudinal sequences of timestamped clinical events to learn adaptable patient representations. Tokenization -- how these timelines are converted into…

Individual-level human mobility prediction has emerged as a significant topic of research with applications in infectious disease monitoring, child, and elderly care. Existing studies predominantly focus on the microscopic aspects of human…

Urban planning designs land-use configurations and can benefit building livable, sustainable, safe communities. Inspired by image generation, deep urban planning aims to leverage deep learning to generate land-use configurations. However,…

Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action…

Spatio-temporal machine learning is critically needed for a variety of societal applications, such as agricultural monitoring, hydrological forecast, and traffic management. These applications greatly rely on regional features that…

The widespread adoption of location-based services has led to the generation of vast amounts of mobility data, providing significant opportunities to model user movement dynamics within urban environments. Recent advancements have focused…

Deep learning has significantly advanced building segmentation in remote sensing, yet models struggle to generalize on data of diverse geographic regions due to variations in city layouts and the distribution of building types, sizes and…

Place classification is a fundamental ability that a robot should possess to carry out effective human-robot interactions. It is a nontrivial classification problem which has attracted many research. In recent years, there is a high…

In this paper, we focus on motion discrete tokenization, which converts raw motion into compact discrete tokens--a process proven crucial for efficient motion generation. In this paradigm, increasing the number of tokens is a common…

In this paper, we present the ``joint pre-training and local re-training'' framework for learning and applying multi-source knowledge graph (KG) embeddings. We are motivated by the fact that different KGs contain complementary information…

Unsupervised feature learning often finds low-dimensional embeddings that capture the structure of complex data. For tasks for which prior expert topological knowledge is available, incorporating this into the learned representation may…

Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via…

Demographic data, such as income, education level, and employment rate, contain valuable information of urban regions, yet few studies have integrated demographic information to generate region embedding. In this study, we show how the…

Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features. This is typically done through image retrieval, where the query is matched to the most similar images from a…

Powerful sentence encoders trained for multiple languages are on the rise. These systems are capable of embedding a wide range of linguistic properties into vector representations. While explicit probing tasks can be used to verify the…

Although haptic sensing has recently been used for legged robot localization in extreme environments where a camera or LiDAR might fail, the problem of efficiently representing the haptic signatures in a learned prior map is still open.…

Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use image-level…

In forecasting multiple time series, accounting for the individual features of each sequence can be challenging. To address this, modern deep learning methods for time series analysis combine a shared (global) model with local layers,…