Lin

Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding. In practice, however, block-wise dLLM inference exposes a…

Graph neural networks (GNNs) are emerging for machine learning research on graph-structured data. GNNs achieve state-of-the-art performance on many tasks, but they face scalability challenges when it comes to real-world applications that…

Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of…

Pre-training datasets are typically collected from web content and lack inherent domain divisions. For instance, widely used datasets like Common Crawl do not include explicit domain labels, while manually curating labeled datasets such as…

This chapter presents perspectives for challenges and future development in building reliable AI systems, particularly, agentic AI systems. Several open research problems related to mitigating the risks of cascading failures are discussed.…

This chapter bridges technical analysis and organizational preparedness by tracing the path from layered failure modes to reliability awareness in generative and agentic AI systems. We first introduce an 11-layer failure stack, a structured…

Diffusion models have shown remarkable success across generative tasks, yet their high computational demands challenge deployment on resource-limited platforms. This paper investigates a critical question for compute-optimal diffusion model…

Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to be loaded to onboard processing elements during computation.…

Dynamic 3D Gaussian splatting (3DGS) extends static 3DGS to render dynamic scenes, enabling AR/VR applications with moving objects. However, implementing dynamic 3DGS on edge devices faces challenges: (1) Loading all Gaussian parameters…

Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As…

This paper focuses on using few-shot learning to improve the accuracy of classifying OCT diagnosis images with major and rare classes. We used the GAN-based augmentation strategy as a baseline and introduced several novel methods to further…

Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficient training techniques. In this paper, we propose…

In recent years, deep neural networks (DNNs) have demonstrated remarkable performance in pathology applications, potentially even outperforming expert pathologists due to their ability to learn subtle features from large datasets. One…

Deep learning assisted digital pathology has the potential to impact clinical practice in significant ways. In recent studies, deep neural network (DNN) enabled analysis outperforms human pathologists. Increasing sizes and complexity of the…

With recent advancements in the development of artificial intelligence applications using theories and algorithms in machine learning, many accurate models can be created to train and predict on given datasets. With the realization of the…

In the era of sustainable transportation, the significance of electric vehicles (EVs) and their battery technology is becoming increasingly paramount. This study addresses the critical aspect of EV battery reliability, an essential factor…

Boosting the task accuracy of tiny neural networks (TNNs) has become a fundamental challenge for enabling the deployments of TNNs on edge devices which are constrained by strict limitations in terms of memory, computation, bandwidth, and…

The classical Multiplicative Ergodic Theorem (MET) of Oseledets is generalized here to cocycles taking values in a semi-finite von Neumann algebra. This allows for a continuous Lyapunov distribution.

Making an inventory of the Solar System is one of the four fundamental science requirements for the Large Synoptic Survey Telescope (LSST). The current baseline footprint for LSST's main Wide-Fast-Deep (WFD) Survey observes the sky below…

Making an inventory of the Solar System is one of the four pillars that the requirements for the Large Synoptic Survey Telescope (LSST) are built upon. The choice between same-filter nightly pairs or different-filter nightly pairs in the…