Computer Science

TechTalk – Optimizing Distributed Large Model Training in AI Clouds

Innovation Wing Two, TechTalk / By

December 12, 2024 (Thursday) 4:30-5:30pm
Distributed training using a large number of devices has been widely adopted for learning large deep learning models. Improving distributed training efficiency is critical for time, resource and energy consumption of large model learning. In this talk, I will introduce recent research works in my group on optimizing distributed training parallelisms for effective training acceleration and maximal resource utilization. Especially, we have designed optimized strategies and systems for operator sharding, computation and communication scheduling for SPMD parallelism (e.g., in Mixture-of-Experts model training) in both homogeneous and heterogeneous AI clusters, as well as dynamic micro-batching and pipelining to tackle sequence length variation in multi-task model training (e.g., Large Language Model training).

TechTalk – Medical Image Representation Learning via Cross-supervision between Images and Text Reports

Innovation Wing Two, TechTalk / By

December 5, 2024 (Thursday) 4:30-5:30pm
Pre-training lays the foundation for recent successes in radiograph analysis supported by deep learning. It learns transferable image representations by conducting large-scale fully- or self-supervised learning on a source domain; however, supervised pre-training requires a complex and labour-intensive two-stage human-assisted annotation process, whereas self-supervised learning cannot compete with the supervised paradigm. To tackle these issues, we propose a cross-supervised methodology called reviewing free-text reports for supervision (REFERS), which acquires free supervision signals from the original radiology reports accompanying the radiographs. The proposed approach employs a vision transformer and is designed to learn joint representations from multiple views within every patient study. REFERS outperforms its transfer learning and self-supervised learning counterparts on four well-known X-ray datasets under extremely limited supervision. Moreover, REFERS even surpasses methods based on a source domain of radiographs with human-assisted structured labels; it therefore has the potential to replace canonical pre-training methodologies.

Young Scholar TechTalk – GRAINS: Proximity Sensing of Objects in Granular Materials

Innovation Wing Two, TechTalk / By

October 17, 2023 (Tuesday) 4:30-5:30pm
Proximity sensing is a method of detecting the presence of objects without making physical contact. However, this concept has not been widely explored in the context of granular materials, which are materials composed of small particles like sand or gravel. This is because granular materials have complex properties and the sensing needs to work without the aid of vision. In this presentation, I will introduce a system called GRAINS (Granular Material-Embedded Autonomous Proximity Sensing). GRAINS is designed to sense objects buried within granular materials by utilizing fundamental principles related to the behavior of granules, such as how they flow like a fluid, how they can become jammed. GRAINS uses force signals to determine the proximity of buried objects. It achieves this by analyzing force anomalies that occur when granules become jammed due to their proximity to objects. These force anomalies are learned in real-time by the system using a mathematical technique called Gaussian process regression. To capture these patterns, a probe is moved along a spiral trajectory within the granular material. The results of our experiments demonstrate that GRAINS can adaptively adjust its parameters to effectively work with different types of granules. It can perceive objects in the nearby vicinity, approximately 0.5 to 7 cm ahead, without the need for direct contact with the buried obstacles.
(project page: https://sites.google.com/view/grains2/home)

Young Scholar TechTalk – Secure and High-performance AI Serving: Protecting AI Secretes, Accelerating AI Insights

Innovation Wing Two, TechTalk / By

September 19, 2023 (Tuesday) 4:30-5:30pm
Driven by the remarkable success of artificial intelligence (AI) and edge computing, the deployment of well-trained private AI models on third-party edge devices for mission-critical applications has become increasingly prevalent. Safeguarding these private models on untrusted devices, while simultaneously speeding up model serving (i.e., inference) through accelerators like GPUs, has escalated in urgency.
We introduce SOTER, a new AI serving system that, for the first time, achieves both high security and high performance. Harnessing the associativity property of AI operators, SOTER presents an innovative approach—transforming computationally expensive AI operators into parameter-morphed equivalents for secure execution on untrusted but fast GPUs, and losslessly restoring inference results within trusted execution environments (TEEs) in CPUs. Experimental results on six prevalent AI models in the three most popular categories show that, even with stronger model protection, SOTER achieves comparable performance with baselines while retaining the same high accuracy as insecure AI model inference.

Young Scholar TechTalk – HOF2 – Interact with Device through Simple and Robust Hand-Over-Face Gesture

Innovation Wing Two, TechTalk / By

Mobile devices have been like an extended part of ourselves, but can we really operate a mobile device just as naturally as how we control our fingers or body? We present HOF2, a novel input modality that uses simple gestures over your face to interact with your device. Unlike other gesture-based modalities, HOF2 is highly robust and can avoid false triggering caused by many unconscious gestures like scratching or wiping, while is still easy, comfortable and natural to use. Moreover, HOF2 is highly available and can be implemented on any mobile phone/tablet/computer with a single camera and without remote servers. In this TechTalk, we will present a live demo on iOS/iPadOS demonstrating the performance of HOF2 scheme in practice and explore some real-life use cases such as virtual conferencing, selfie, or TV controller. We believe there are far more possibilities waiting to be explored with this novel interaction scheme.

TechTalk – Learning Optimal Auctions from Data

Innovation Wing Two, TechTalk / By

The design of optimal auctions for revenue maximization is a central topic in Economics. Classical optimal auction theory assumes that bidders’ values are drawn from a known distribution. In reality, the source of such prior information is really past data. Cole and Roughgarden (2014) modeled past data as i.i.d. samples from the value distribution and asked: How many samples are sufficient/necessary to learn a near optimal auction? This TechTalk will introduce a unified theory that yields sample-efficient algorithms with optimal sample complexity for auctions with homogeneous goods, and state-of-the-art sample complexity for auctions with heterogeneous goods. Unlike conventional statistical learning theory which focuses on the complexity of hypothesis classes, our new theory relies on the simplicity of data distributions and a monotonicity property of these problems.

Young Scholar TechTalk – Learning to Control and Coordinate Hybrid Traffic Through Robot Vehicles at Complex and Unsignalized Intersections

Innovation Wing Two, TechTalk / By

Intersections are essential road infrastructures for traffic in modern metropolises; however, they can also be the bottleneck of traffic flows due to traffic incidents or the absence of traffic coordination mechanisms such as traffic lights. Thus, various control and coordination mechanisms that are beyond traditional control methods have been proposed to improve the efficiency of intersection traffic. Amongst these methods, the control of foreseeable hybrid traffic that consists of human-driven vehicles (HVs) and robot vehicles (RVs) has recently emerged. We propose a decentralized reinforcement learning approach for the control and coordination of hybrid traffic at real-world, complex intersections–a topic that has not been previously explored. Comprehensive experiments are conducted to show the effectiveness of our approach. We show that using 5% RVs, we can prevent congestion formation inside the intersection under the actual traffic demand of 700 vehicles per hour. When there exist more than 50% RVs in traffic, our method starts to outperform traffic signals on the average waiting time of all vehicles at the intersection.

Young Scholar TechTalk – Flexible Learning of Quantum States with Generative Query Neural Networks

Innovation Wing Two, TechTalk / By

Deep neural networks are a powerful tool for the characterization of quantum states. Existing networks are typically trained with experimental data gathered from the specific quantum state that needs to be characterized. In this talk, Mr. Yan Zhu, from Department of Computer Science, will introduce a model of network that can be trained with classically simulated data from a fiducial set of states and measurements, and can later be used to characterize quantum states that share structural similarities with the states in the fiducial set. With little guidance of quantum physics, the network builds its own data-driven representation of quantum states, and then uses it to predict the outcome statistics of quantum measurements that have not been performed yet. The state representation produced by the network can also be used for tasks beyond the prediction of outcome statistics, including clustering of quantum states and identification of different phases of matter.

TechTalk – Causes and Effects in the Microscopic World

Innovation Wing Two, TechTalk / By

Identifying cause-effect relations is a fundamental primitive in a variety of areas of science and technology. The identification of causal relations is generally accomplished through statistical trials where alternative hypotheses about the causal relations are tested against each other. Traditionally, such trials have been based on classical statistics. But while classical statistics effectively describes the behavior of macroscopic variables, it becomes inadequate at the microscopic scale, described by quantum mechanics, where a richer spectrum of causal relations is accessible. In the past years, there has been an increasing interest in the study of causal relations among quantum variables. In this talk, Professor Giulio Chiribella will show that the counterintuitive features of quantum mechanics can be turned to our advantage, providing speed-ups in the identification of causal relations. These speed-ups have applications to the design of automated quantum machines and new quantum communication protocols.

TechTalk – Autonomous Excavation: Manipulation and Perception of Granular Materials

Innovation Wing Two, TechTalk / By

Autonomous excavators are an essential part of the goal of “building the robots that build the world”. One unique problem in autonomous excavation is how to deal with the granular materials like soils and sands, which is seldom studied in robotics. In this talk, Dr. Pan will present his team’s recent work about how to achieve efficient manipulation of soils by optimizing the trajectory of the excavator’s bucket, and how to enable the excavator to be aware of the objects buried in the soils by using a proximity sensing mechanism based on jamming in granular materials.