Portrait de Xue (Steve) Liu n'est pas disponible

Xue (Steve) Liu

Membre académique associé
Professeur titulaire, McGill University, École d'informatique
Vice-président, recherche et développement, directeur scientifique et co-directeur, Samsung's Montreal AI Center
Sujets de recherche
Apprentissage profond

Biographie

Xue (Steve) Liu est professeur titulaire à l'École d'informatique de l’Université McGill, ainsi que vice-président de la recherche et du développement, scientifique en chef et codirecteur du Centre d'IA de Samsung à Montréal. Il est également titulaire d'une bourse William Dawson (professeur titulaire) à l'Université McGill et professeur de mathématiques et de statistiques (nomination de courtoisie) dans le même établissement. Auparavant, il était scientifique en chef chez Tinder Inc., où il dirigeait la recherche et l'innovation touchant l’application de rencontre et de découverte sociale la plus importante au monde, évaluée à plus de 10 milliards de dollars américains.

M. Liu est membre de l'IEEE et membre associé de Mila – Institut québécois d’intelligence artificielle. À l'Université McGill, il est également membre associé du Centre sur les machines intelligentes (CIM) et du Centre sur les systèmes et les technologies avancés en communication (SYTACom). Il a reçu plusieurs récompenses, notamment le prix Mitacs 2017 reconnaissant un leadership exceptionnel parmi le corps professoral, le prix Outstanding Young Canadian Computer Science Researcher de l'Association canadienne de l'informatique en 2014, et le prix Tomlinson Scientist soulignant l'excellence et le leadership scientifique à l'Université McGill. Il est le directeur du Laboratoire sur l’intelligence cyberphysique de l'Université McGill, qu’il a fondé en 2007. Il a également travaillé brièvement en tant que professeur associé de la chaire Samuel R. Thompson au Département d'informatique et d'ingénierie de l'Université du Nebraska à Lincoln, aux laboratoires Hewlett-Packard à Palo Alto, en Californie, et au centre de recherche T. J. Watson d'IBM à New York.

Étudiants actuels

Doctorat - McGill
Co-superviseur⋅e :
Doctorat - McGill
Co-superviseur⋅e :
Doctorat - McGill
Doctorat - McGill
Doctorat - McGill
Doctorat - McGill
Maîtrise recherche - McGill
Doctorat - McGill
Co-superviseur⋅e :
Doctorat - McGill
Doctorat - McGill

Publications

Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation
Senyu Li
Zipeng Sun
Jiayi Wang
Pontus Stenetorp
AIoT Smart Home via Autonomous LLM Agents
Dmitriy Rivkin
Francois Hogan
Amal Feriani
Abhisek Konar
Adam Sigal
The common-sense reasoning abilities and vast general knowledge of large language models (LLMs) make them a natural fit for interpreting use… (voir plus)r requests in a smart home assistant context. LLMs, however, lack specific knowledge about the user and their home, which limits their potential impact. Smart home agent with grounded execution (SAGE), overcomes these and other limitations by using a scheme in which a user request triggers an LLM-controlled sequence of discrete actions. These actions can be used to retrieve information, interact with the user, or manipulate device states. SAGE controls this process through a dynamically constructed tree of LLM prompts, which help it decide which action to take next, whether an action was successful, and when to terminate the process. The SAGE action set augments an LLM’s capabilities to support some of the most critical requirements for a smart home assistant. These include: flexible and scalable user preference management (“Is my team playing tonight?”), access to any smart device’s full functionality without device-specific code via API reading (“Turn down the screen brightness on my dryer”), persistent device state monitoring (“Remind me to throw out the milk when I open the fridge”), natural device references using only a photo of the room (“Turn on the lamp on the dresser”), and more. We introduce a benchmark of 50 new and challenging smart home tasks where SAGE achieves a 76% success rate, significantly outperforming existing LLM-enabled baselines (30% success rate).
AIoT Smart Home via Autonomous LLM Agents
Dmitriy Rivkin
Francois Hogan
Amal Feriani
Abhisek Konar
Adam Sigal
ParetoFlow: Guided Flows in Multi-Objective Optimization
Ye Yuan
Can Chen
In offline multi-objective optimization (MOO), we leverage an offline dataset of designs and their associated labels to simultaneously minim… (voir plus)ize multiple objectives. This setting more closely mirrors complex real-world problems compared to single-objective optimization. Recent works mainly employ evolutionary algorithms and Bayesian optimization, with limited attention given to the generative modeling capabilities inherent in such data. In this study, we explore generative modeling in offline MOO through flow matching, noted for its effectiveness and efficiency. We introduce ParetoFlow, specifically designed to guide flow sampling to approximate the Pareto front. Traditional predictor (classifier) guidance is inadequate for this purpose because it models only a single objective. In response, we propose a multi-objective predictor guidance module that assigns each sample a weight vector, representing a weighted distribution across multiple objective predictions. A local filtering scheme is introduced to address non-convex Pareto fronts. These weights uniformly cover the entire objective space, effectively directing sample generation towards the Pareto front. Since distributions with similar weights tend to generate similar samples, we introduce a neighboring evolution module to foster knowledge sharing among neighboring distributions. This module generates offspring from these distributions, and selects the most promising one for the next iteration. Our method achieves state-of-the-art performance across various tasks.
Robust Guided Diffusion for Offline Black-Box Optimization
Can Chen
Christopher Beckham
Zixuan Liu
Offline black-box optimization aims to maximize a black-box function using an offline dataset of designs and their measured properties. Two … (voir plus)main approaches have emerged: the forward approach, which learns a mapping from input to its value, thereby acting as a proxy to guide optimization, and the inverse approach, which learns a mapping from value to input for conditional generation. (a) Although proxy-free~(classifier-free) diffusion shows promise in robustly modeling the inverse mapping, it lacks explicit guidance from proxies, essential for generating high-performance samples beyond the training distribution. Therefore, we propose \textit{proxy-enhanced sampling} which utilizes the explicit guidance from a trained proxy to bolster proxy-free diffusion with enhanced sampling control. (b) Yet, the trained proxy is susceptible to out-of-distribution issues. To address this, we devise the module \textit{diffusion-based proxy refinement}, which seamlessly integrates insights from proxy-free diffusion back into the proxy for refinement. To sum up, we propose \textit{\textbf{R}obust \textbf{G}uided \textbf{D}iffusion for Offline Black-box Optimization}~(\textbf{RGD}), combining the advantages of proxy~(explicit guidance) and proxy-free diffusion~(robustness) for effective conditional generation. RGD achieves state-of-the-art results on various design-bench tasks, underscoring its efficacy. Our code is at https://anonymous.4open.science/r/RGD-27A5/README.md.
ParetoFlow: Guided Flows in Multi-Objective Optimization
Ye Yuan
Can Chen
In offline multi-objective optimization (MOO), we leverage an offline dataset of designs and their associated labels to simultaneously minim… (voir plus)ize multiple objectives. This setting more closely mirrors complex real-world problems compared to single-objective optimization. Recent works mainly employ evolutionary algorithms and Bayesian optimization, with limited attention given to the generative modeling capabilities inherent in such data. In this study, we explore generative modeling in offline MOO through flow matching, noted for its effectiveness and efficiency. We introduce ParetoFlow, specifically designed to guide flow sampling to approximate the Pareto front. Traditional predictor (classifier) guidance is inadequate for this purpose because it models only a single objective. In response, we propose a multi-objective predictor guidance module that assigns each sample a weight vector, representing a weighted distribution across multiple objective predictions. A local filtering scheme is introduced to address non-convex Pareto fronts. These weights uniformly cover the entire objective space, effectively directing sample generation towards the Pareto front. Since distributions with similar weights tend to generate similar samples, we introduce a neighboring evolution module to foster knowledge sharing among neighboring distributions. This module generates offspring from these distributions, and selects the most promising one for the next iteration. Our method achieves state-of-the-art performance across various tasks.
ParetoFlow: Guided Flows in Multi-Objective Optimization
Ye Yuan
Can Chen
In offline multi-objective optimization (MOO), we leverage an offline dataset of designs and their associated labels to simultaneously minim… (voir plus)ize multiple objectives. This setting more closely mirrors complex real-world problems compared to single-objective optimization. Recent works mainly employ evolutionary algorithms and Bayesian optimization, with limited attention given to the generative modeling capabilities inherent in such data. In this study, we explore generative modeling in offline MOO through flow matching, noted for its effectiveness and efficiency. We introduce ParetoFlow, specifically designed to guide flow sampling to approximate the Pareto front. Traditional predictor (classifier) guidance is inadequate for this purpose because it models only a single objective. In response, we propose a multi-objective predictor guidance module that assigns each sample a weight vector, representing a weighted distribution across multiple objective predictions. A local filtering scheme is introduced to address non-convex Pareto fronts. These weights uniformly cover the entire objective space, effectively directing sample generation towards the Pareto front. Since distributions with similar weights tend to generate similar samples, we introduce a neighboring evolution module to foster knowledge sharing among neighboring distributions. This module generates offspring from these distributions, and selects the most promising one for the next iteration. Our method achieves state-of-the-art performance across various tasks.
Health satisfaction outcome from integrated autonomous mobile clinics
Yuzhang Huang
Shaoshan Liu
Zhongying Pan
Carl Wu
Herng-Chia Chiu
Leiyu Shi
Robust Guided Diffusion for Offline Black-Box Optimization
Can Chen
Christopher Beckham
Zixuan Liu
Offline black-box optimization aims to maximize a black-box function using an offline dataset of designs and their measured properties. Two … (voir plus)main approaches have emerged: the forward approach, which learns a mapping from input to its value, thereby acting as a proxy to guide optimization, and the inverse approach, which learns a mapping from value to input for conditional generation. (a) Although proxy-free~(classifier-free) diffusion shows promise in robustly modeling the inverse mapping, it lacks explicit guidance from proxies, essential for generating high-performance samples beyond the training distribution. Therefore, we propose \textit{proxy-enhanced sampling} which utilizes the explicit guidance from a trained proxy to bolster proxy-free diffusion with enhanced sampling control. (b) Yet, the trained proxy is susceptible to out-of-distribution issues. To address this, we devise the module \textit{diffusion-based proxy refinement}, which seamlessly integrates insights from proxy-free diffusion back into the proxy for refinement. To sum up, we propose \textit{\textbf{R}obust \textbf{G}uided \textbf{D}iffusion for Offline Black-box Optimization}~(\textbf{RGD}), combining the advantages of proxy~(explicit guidance) and proxy-free diffusion~(robustness) for effective conditional generation. RGD achieves state-of-the-art results on various design-bench tasks, underscoring its efficacy. Our code is at https://github.com/GGchen1997/RGD.
A Survey of Diversification Techniques in Search and Recommendation
Haolun Wu
Yansen Zhang
Chen Ma
Fuyuan Lyu
Bowei He
Bhaskar Mitra
Diversifying search results is an important research topic in retrieval systems in order to satisfy both the various interests of customers … (voir plus)and the equal market exposure of providers. There has been a growing attention on diversity-aware research during recent years, accompanied by a proliferation of literature on methods to promote diversity in search and recommendation. However, the diversity-aware studies in retrieval systems lack a systematic organization and are rather fragmented. In this survey, we are the first to propose a unified taxonomy for classifying the metrics and approaches of diversification in both search and recommendation, which are two of the most extensively researched fields of retrieval systems. We begin the survey with a brief discussion of why diversity is important in retrieval systems, followed by a summary of the various diversity concerns in search and recommendation, highlighting their relationship and differences. For the survey’s main body, we present a unified taxonomy of diversification metrics and approaches in retrieval systems, from both the search and recommendation perspectives. In the later part of the survey, we discuss the openness research questions of diversity-aware research in search and recommendation in an effort to inspire future innovations and encourage the implementation of diversity in real-world systems.
Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval
Haolun Wu
Ofer Meshi
Masrour Zoghi
Craig Boutilier
MARYAM KARIMZADEHGAN
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
Ziquan Liu
Yufei Cui
Yan Yan
Yi Xu
Xiangyang Ji
Antoni B. Chan
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient healt… (voir plus)h and road safety, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks and reliable uncertainty quantification in decision-making. With extensive research focused on enhancing adversarial robustness through various forms of adversarial training (AT), a notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. To address this gap, this study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks within the adversarial defense community. It is first unveiled that existing CP methods do not produce informative prediction sets under the commonly used