相关论文: Pre-trained Transformer Uncovers Meaningful Patter…

Predicting individuals' next locations is a core task in human mobility modelling, with wide-ranging implications for urban planning, transportation, public policy and personalised mobility services. Traditional approaches largely depend on…

Machine learning models underpin many modern financial systems for use cases such as fraud detection and churn prediction. Most are based on supervised learning with hand-engineered features, which relies heavily on the availability of…

Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because language pretraining preconditions time series training with a reusable manifold. A…

The challenge of traversability estimation is a crucial aspect of autonomous navigation in unstructured outdoor environments such as forests. It involves determining whether certain areas are passable or risky for robots, taking into…

Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. This process consists of taking a neural network pre-trained on a large feature-rich source…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

Deep learning methods have advanced quickly in brain imaging analysis over the past few years, but they are usually restricted by the limited labeled data. Pre-trained model on unlabeled data has presented promising improvement in feature…

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

Recent work has shown that transformer-based language models learn rich geometric structure in their embedding spaces. In this work, we investigate whether sentence embeddings exhibit structured geometric organization aligned with…

This paper aims to improve the computational efficiency of motion planning for mobile robots with non-trivial dynamics through the use of learned controllers. Offline, a system-specific controller is first trained in an empty environment.…

Large mobility datasets collected from various sources have allowed us to observe, analyze, predict and solve a wide range of important urban challenges. In particular, studies have generated place representations (or embeddings) from…

Human mobility modeling is critical for urban planning and transportation management, yet existing approaches often lack the integration capabilities needed to handle diverse data sources. We present a foundation model framework for…

Despite their stellar performance on a wide range of tasks, including in-context tasks only revealed during inference, vanilla transformers and variants trained for next-token predictions (a) do not learn an explicit world model of their…

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.…

Human mobility plays a crucial role in transportation, urban planning, and public health. Advances in deep learning and the availability of diverse mobility data have transformed mobility modeling. However, existing deep learning models…

The massive amounts of geolocation data collected from mobile phone records has sparked an ongoing effort to understand and predict the mobility patterns of human beings. In this work, we study the extent to which social phenomena are…

Predicting human mobility holds significant practical value, with applications ranging from enhancing disaster risk planning to simulating epidemic spread. In this paper, we present the GeoFormer, a decoder-only transformer model adapted…

Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…

In human-level NLP tasks, such as predicting mental health, personality, or demographics, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within modern transformer-based language models,…

Encrypted traffic classification (TC) methods must adapt to new protocols and extensions as well as to advancements in other machine learning fields. In this paper, we adopt a transfer learning setup best known from computer vision. We…