Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings (PE), such as RoPE, need extrapolating to unseen positions which degrades performance when the inference resolution differs from training. In this paper, We propose a Length-Extrapolatable Diffusion Transformer (LEDiT) to overcome this limitation. LEDiT needs no explicit PEs, thereby avoiding PE extrapolation. The key innovation of LEDiT lies in the use of causal attention. We demonstrate that causal attention can implicitly encode global positional information and show that such information facilitates extrapolation. We further introduce a locality enhancement module, which captures fine-grained local information to complement the global coarse-grained position information encoded by causal attention. Experimental results on both conditional and text-to-image generation tasks demonstrate that LEDiT supports up to 4× resolution scaling (e.g., from 256$\times$256 to 512$\times$512), achieving better image quality compared to the state-of-the-art length extrapolation methods. We believe that LEDiT marks a departure from the standard RoPE-based methods and offers a promising insight into length extrapolation. Project page: https://shenzhang2145.github.io/ledit/

In human activity recognition (HAR), activity labels have typically been encoded in one-hot format, which has a recent shift towards using textual representations to provide contextual knowledge. Here, we argue that HAR should be anchored to physical motion data, as motion forms the basis of activity and applies effectively across sensing systems, whereas text is inherently limited. We propose SKELAR, a novel HAR framework that pretrains activity representations from skeleton data and matches them with heterogeneous HAR signals. Our method addresses two major challenges: (1) capturing core motion knowledge without context-specific details. We achieve this through a self-supervised coarse angle reconstruction task that recovers joint rotation angles, invariant to both users and deployments; (2) adapting the representations to downstream tasks with varying modalities and focuses. To address this, we introduce a self-attention matching module that dynamically prioritizes relevant body parts in a data-driven manner. Given the lack of corresponding labels in existing skeleton data, we establish MASD, a new HAR dataset with IMU, WiFi, and skeleton, collected from 20 subjects performing 27 activities. This is the first broadly applicable HAR dataset with time-synchronized data across three modalities. Experiments show that SKELAR achieves the state-of-the-art performance in both full-shot and few-shot settings. We also demonstrate that SKELAR can effectively leverage synthetic skeleton data to extend its use in scenarios without skeleton collections.

Motion time series collected from low-power, always-on mobile and wearable devices such as smartphones and smartwatches offer significant insights into human behavioral patterns, with wide applications in healthcare, automation, IoT, and AR/XR. However, given security and privacy concerns, building large-scale motion time series datasets remains difficult, hindering the development of pre-trained models for human activity analysis. Typically, existing models are trained and tested on the same dataset, leading to poor generalizability across variations in device location, device mounting orientation, and human activity type. In this paper, we introduce UniMTS, the first unified pre-training procedure for motion time series that generalizes across diverse device latent factors and activities. Specifically, we employ a contrastive learning framework that aligns motion time series with text descriptions enriched by large language models. This helps the model learn the semantics of time series to generalize across activities. Given the absence of large-scale motion time series data, we derive and synthesize time series from existing motion skeleton data with all-joint coverage. We use spatio-temporal graph networks to capture the relationships across joints for generalization across different device locations. We further design rotation-invariant augmentation to make the model agnostic to changes in device mounting orientations. Our model shows exceptional generalizability across 18 motion time series classification benchmark datasets, outperforming the best baselines by 340% in the zero-shot setting, 16.3% in the few-shot setting, and 9.2% in the full-shot setting.

Real-world deployment of federated learning requires orchestrating clients with widely varied compute resources, from strong enterprise-grade devices in data centers to weak mobile and Web-of-Things devices. Prior works have attempted to downscale large models for weak devices and aggregate shared parts among heterogeneous models. A typical architectural assumption is that there are equally many strong and weak devices. In reality, however, we often encounter resource skew where a few (1 or 2) strong devices hold substantial data resources, alongside many weak devices. This poses challenges-the unshared portion of the large model rarely receives updates or gains benefits from weak collaborators.

Cyber-physical systems are starting to adopt neural network (NN) models for a variety of smart sensing applications. While several efforts seek better NN architectures for system performance improvement, few attempts have been made to study the deployment of these systems in the field. Proper deployment of these systems is critical to achieving ideal performance, but the current practice is largely empirical via trials and errors, lacking a measure of quality. Sensing quality should reflect the impact on the performance of NN models that drive machine perception tasks. However, traditional approaches either evaluate statistical difference that exists objectively, or model the quality subjectively via human perception.

Discovering patterns in time series data is essential to many key tasks in intelligent sensing systems, such as human activity recognition and event detection. These tasks involve the classification of sensory information from physical measurements such as inertial or temperature change measurements. Due to differences in the underlying physics, existing methods for classification use handcrafted features combined with traditional learning algorithms, or employ distinct deep neural models to directly learn from raw data.

Smart Building Technologies hold promise for better livability for residents and lower energy footprints. Yet, the rollout of these technologies, from demand response controls to fault detection and diagnosis, significantly lags behind and is impeded by the current practice of manual identification of sensing point relationships, e.g., how equipment is connected or which sensors are co-located in the same space. This manual process is still error-prone, albeit costly and laborious.We study relation inference among sensor time series. Our key insight is that, as equipment is connected or sensors co-locate in the same physical environment, they are affected by the same real-world events, e.g., a fan turning on or a person entering the room, thus exhibiting correlated changes in their time series data. To this end, we develop a deep metric learning solution that first converts the primitive sensor time series to the frequency domain, and then optimizes a representation of sensors that encodes their relations. Built upon the learned representation, our solution pinpoints the relationships among sensors via solving a combinatorial optimization problem. Extensive experiments on real-world buildings demonstrate the effectiveness of our solution.