Abstract: Light is an electromagnetic spectrum that spans a wide range of wavelengths, including ultraviolet, visible, infrared, thermal wavelengths, and so on. Human vision is restricted to the visible wavelengths, but light interacts a lot more richly in the infrared and thermal wavelengths. Moreover, thermal images are clear even in harsh weather conditions like rain...

Abstract: Computational intelligence is empowering many critical society applications in health, education, transportations, manufacturing, etc. The intelligent computing techniques are required to be socially responsible in terms of safety, fairness, sustainability, etc. To meet these requirements, the computing operators need to make context-aware decisions on computing resource allocation. Importantly, the decisions must be trustworthy in...

Abstract: The capacity to sense light polarization generally accompanies a reduction in resolution. Inspired by the rapid signal processing of insects with small brains, and the fact that some insects may sense polarization without polarization-selective sensors, the Vuong MMO Lab studies how nanostructures spatially transform polarization through scattering. Compressed sensing of both incident direction and...

Abstract: Given the advancements in artificial intelligence over the last decade along with the significant decrease in hardware cost, indoor service robots such as Roombas are increasingly becoming a part of our lives. In this talk, I will highlight my lab's recent efforts towards developing AI for such autonomous agents. First, I will discuss an...

Abstract: Modern intelligent systems, such as social robots and autonomous vehicles, interact frequently with humans. Their behaviors are highly complex and dynamic, which results from unobservable social interactions. Thus, building reliable autonomy that safely navigates multi-agent scenarios requires scalable and generalizable relational reasoning and interaction modeling between interactive agents. Meanwhile, robots should be able to...

Abstract: Recent progress in large language models (LLMs) calls for a thorough safety inspection of these models. In this talk, I will discuss three of our recent works on adversarial attacks related to natural languages. We first review common concepts of jailbreaking LLMs and discuss the trade-offs between their usefulness and safety. Then, we move...

Abstract: Pretrain-finetune has emerged as a powerful learning paradigm, achieving remarkable accuracy gains in various domains. However, its substantial computational requirements limit its application to broader areas. To address this challenge, we develop MixTraining, a novel training framework that---for the first time---incorporates asynchronous computation into the standard pretrain-finetune paradigm. At a high level, our MixTraining...

Abstract: Artificial intelligence and machine learning models have experienced a transformative evolution in capability and deployment. Recently, large-scale models trained on expansive datasets have revolutionized numerous domains, from online search to media creation. However, with the growing power of these AI systems, the urgency to address their security concerns has also escalated. Understanding and fortifying...

Abstract: Markov chain Monte Carlo (MCMC) requires only the ability to evaluate the likelihood, making it a common technique for inference in complex models. However, it can have a slow mixing rate, requiring the generation of many samples to obtain good estimates and an overall high computational cost. In this talk, I will present a...

Abstract: In this talk, I will introduce R^3, a new system that helps robots learn and make decisions faster and more efficiently right where they operate. R^3 smartly manages the robot's learning process by adjusting how much data it processes and remembers, ensuring it doesn't run out of memory. This is crucial for robots that...

Abstract: Using advanced 3D sensors and sophisticated deep learning models, autonomous systems such as self-driving cars, delivery drones are already transforming our daily life. However, a significant remaining challenge for further advancement is the reliability, robustness, and the ability to anticipate and handle long-tail events and corner-cases. Humans, on the other hand, are extremely good...

Abstract: Scene understanding using multi-modal data is necessary in many applications, e.g., autonomous navigation. To achieve this in a variety of situations, existing models must be able to adapt to shifting data distributions without arduous data annotation. Current approaches assume that the source data is available during adaptation and that the source consists of paired...