Home
Topics
Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Available Speakers and their Lectures on this Topic

Rizwan Ahmed – Nagpur, India

AI -The Key to Scaling Cyber Defence... Systematic identification, Intelligent automation, Ability to action and Use Cases
This talk will cover various technical aspects related to Artificial Intelligence for scaling Cyber Security. This talk will cover following specific...
Artificial Intelligence: Opportunities & Threats
This talk will cover various technical aspects related to Artificial Intelligence. This talk will cover following specific...

David Atienza – Lausanne, Switzerland

Biologically-Inspired IoT Systems for Federated Learning-Based Healthcare
Internet of Things (IoT) is the next frontier of innovation where our everyday objects are connected in ways that improve our lives and can transform industries, in particular healthcare and...

Ahmedullah Aziz – Knoxville, TN, United States

AI for Better Hardware & Hardware for Better AI
For years, the rapid ascent of AI has captivated the world, but behind every groundbreaking algorithm lies an unsung hero: hardware. While software and algorithms have stolen the spotlight, the...

Ricardo Baeza-Yates – Palo Alto, CA, United States

Bias and the Web
The Web is the most powerful communication medium and the largest public data repository that humankind has created. Its content ranges from great reference sources such as Wikipedia to ugly fake...
Big Data or Right Data? Opportunities and Challenges
Big data nowadays is a fashionable topic, independently of what people mean when they use this term. But being big is just a matter of volume, although there is no clear agreement in the size...
Distributed Web Search
In the ocean of Web data, Web search engines are the primary way to access content. As the data is on the order of petabytes, current search engines are very large centralized systems based on...
Ethics in AI: A Challenging Task
In the first part we cover current specific challenges: (1) discrimination (e.g., facial recognition, justice, sharing economy, language models); (2) phrenology (e.g., biometric based...
Responsible AI
In the first part we cover five current specific problems that motivate the needs of responsible AI: (1) discrimination (e.g., facial recognition, justice, sharing economy, language models); (2)...
Semantic Search
Semantic search lies in the cross roads of information retrieval and natural language

processing and is the current frontier of search technology. The first part consists in...

Mehdi Bahrami – Santa Clara, CA, United States

A Hands-On Workshop: Building Advanced AI Applications and Agents in One Hour
This workshop combines the best of two engaging sessions, offering a comprehensive and hands-on experience in building advanced AI applications and AI agents. We will use the state-of-the-art...
Advancing AGI: From Training and Fine-Tuning to Interactive Agent Development
This talk begins by tracing the history of Artificial General Intelligence (AGI) and discusses potential advancements and future directions. AGI can enhance not only the capability of...
Discovering Bias in Large Language Models (LLMs)
The rapid proliferation of large language models (LLMs) has brought with it both opportunities and challenges. While LLMs and more broadly generative AI technologies are capable of...

Nelly Bencomo – Durham, United Kingdom

Bayesian Theory of Surprise to Quantify Degrees of Uncertainty
In the specific area of software engineering (SE) for self-adaptive systems (SASs) there is a growing research awareness about the synergy between SE and artificial intelligence (AI). We are just...
Decision-Making under Uncertainty: Human-Machine Teaming
There is growing uncertainty about the environment of software systems. Therefore, how the system should behave under different contexts cannot be fully predicted at design time. It is...

Duncan P Brumby – London, United Kingdom

Generative AI: Lessons from Dickens for the Information Age
Generative AI is transforming how we work, learn, and create, offering significant opportunities while raising important ethical and practical challenges. In this timely lecture, Professor...

Margaret Burnett – Corvallis, OR, United States

Mission: To enable diverse mere mortals to assess an AI agent's "goodness" for their own needs

As AI agents become more and more prevalent in everyday technology, more and more individuals -- from every walk of life, at every level of education, across the entire socioeconomic...

Heloisa Candello – Campinas, São Paulo, Brazil

AI conversational agents in operation in human society
The human society is undergoing a significant transformation due to advances in artificial intelligence (AI). These technologies enhance operational processes and customer engagement, enabling...
Artificial Intelligence and social impact
In this talk I invite you to consider how the use of technology can support communities living in vulnerable situations to increase access to financial services. We will discuss and explore...
Generative AI: Design and HCI perspectives
This talk invites reflection on essential human factors to consider when designing conversational user interfaces and generative AI. Through examples of CUI projects and design methods,...
User Methods and Approaches to Design conversational user interfaces
Recent advances in artificial intelligence, natural language processing, and mobile computing, together with the rising popularity of chat and messaging environments, have enabled a boom in the...

Federico Cerutti – Brescia, Italy

Argumentation and Machine Learning: when the Whole is Greater than the Sum of the Parts
Argumentation technology is a rich interdisciplinary area of research that has emerged as one of the most promising paradigms for common sense reasoning and conflict resolution. In this lecture, I...
Enterprise knowledge management in the era of LLMs
This lecture explores how Large Language Models (LLMs) are revolutionising enterprise knowledge management. We begin by examining the evolution of knowledge management systems, from early...
Managing the risks of digital transformation
This lecture examines the critical challenges of managing risks in digital transformation, integrating insights from the NIST Cybersecurity Framework, the NIST AI Risk Management Framework, and...

Eugenio Cesario – Rende (CS), Italy

A machine learning approach to forecast crimes in multi-density crime hotspots
The increasing pervasiveness of ICT technologies and sensor infrastructures is enabling police departments to gather and store increasing...
Big Data Analytics and Smart Cities: Applications, Challenges and Opportunities
The steadily increasing urbanization is causing significant economic and social transformations in urban areas, posing several challenges and...

Tanmoy Chakraborty – New Delhi, India

Combating Hostile Posts on Social Media: Detection, Characterization, Mitigation, and Beyond
Online social media platforms are popular mediums for the dissemination and consumption of information. Unfortunately, due to decentralized generation and propagation of content, they also come...
Evolution of Large Language Models: The Good, The Bad and The Opportunities
In recent years, the field of natural language processing has seen a revolution with the development of large language models (LLMs) such as BERT, GPT-3, T5, and others. These models have been...
Social Network Analysis: Introduction, Network Properties, and Applications
The social network, being a major part of online media, has emerged with several avatars in providing a variety of services -- virtual networking sites (e.g., Facebook, LinkedIn), microblogs...
Transforming Mental Health Care with AI and Language Technology
Mental health issues are rising at an alarming rate. A recent report reveals that one out of six people suffers from mental health related issues. At the same time, there is a severe shortage...

Polo Chau – Atlanta, GA, United States

Secure and Interpretable AI: Scalable Interactive and Practical Tools

We have witnessed tremendous growth in Artificial intelligence (AI) and machine learning (ML) recently. However, research shows that AI and ML models are often vulnerable to...

Geeta Chauhan – Santa Clara, CA, United States

AI @ Edge using Intel NCS
The new generation of hardware accelerators are enabling rich AI driven, Intelligent IoT solutions @ the edge.

The talk will showcase how to use...
Best Practices for On-Demand HPC
Traditionally HPC has been popular in Scientific domains, but not in most other Enterprises. With the advent of on-demand-HPC in cloud and growing adoption of Deep Learning, HPC should now...
Decentralized AI: Convergence of Blockchain and AI
As we move into a world where User's will own their own data, and companies will use "Ethically Sourced Data", there will be a rampant need for Decentralized AI. And,...
Deep Learning for Medical Imaging
The talk covers use cases, special challenges and solutions for Deep Learning for Medical Image Analysis. You will learn about:

- Use cases for Deep...
Distributed Deep Learning Optimizations
This talk will cover how to build and deploy distributed deep learning models at scale. You will learn how to parallelize your models, and techniques for optimizing your cluster for faster...

Nitesh Chawla – Notre Dame, IN, United States

Harnessing Artificial Intelligence for Scientific Discovery: Challenges and Opportunities in Chemistry
Artificial Intelligence (AI) is rapidly advancing scientific research across fields, with graph neural networks (GNNs) and large language models (LLMs), particularly those trained on multimodal...
Learning from Imbalanced Data: Progress and Challenges
Despite over two decades of progress, imbalanced data is still considered a significant challenge for contemporary machine learning models. With modern advances and rapid developments in deep...
Learning on Graphs
Graphs are ubiquitous across a variety of use-cases, and have emerged as a powerful means of representing complex systems. Graph Neural Networks have demonstrated exceptional effectiveness in...
Traversing the Journey of Data and AI: From Convergence to Translation
In this talk, I will present our work on fundamental advances in AI, inspired by interdisciplinary problem statements and societal challenges. I will also highlight our innovation journey that...

Junying Chen – Guangzhou, China

Research Progress and Application of Lightweight Neural Networks
Convolutional neural networks (CNNs) have achieved unmatched performance in many applications such as image classification, object detection, and semantic segmentation. Current research trend of...
Research and Medical Application of Vision Transformer and Capsule Network Models
Vision Transformer and capsule network models are deep learning models that have attracted much attention in recent years. Vision Transformer uses a self-attention mechanism to assign different...

Pin-Yu Chen – WHITE PLAINS, NY, United States

Exploring Safety Risks in Large Language Models and Generative AI
Large language models (LLMs) and Generative AI (GenAI) are at the forefront of current AI research and technology. With their rapidly increasing popularity and availability, challenges and...

Betty H.C. Cheng – East Lansing, MI, United States

Applying Model-Driven Requirements Engineering to Manage Uncertainty for High-Assurance Self-Adaptive Systems: Lessons Learned and Research Challenges
This presentation will overview several research projects that explore how model-driven requirements engineering can been used to model, analyze, and mitigate uncertainty arising in three...
Be careful what you wish for...When should we trust AI?
Trustworthy artificial intelligence (Trusted AI) is essential when autonomous, safety-critical systems use learning-enabled components (LECs) in uncertain environments. When reliant on deep...
Search-Based Software Engineering for Learning-Enabled Self-Adaptive Systems
Trustworthy artificial intelligence (Trusted AI) is essential when autonomous, safety-critical systems use learning-enabled components (LECs) in uncertain environments. When reliant on deep...
Software Engineering for Learning-Enabled Self-Adaptive Systems
Trustworthy artificial intelligence (Trusted AI) is essential when autonomous, safety-critical systems use learning-enabled components (LECs) in uncertain environments. When reliant on deep...

Aswani Kumar Cherukuri – Vellore, India

Spill the beans: Artificial Intelligence (AI), Machine Learning (ML) & Deep Learning (DL)
With rapid developments in the field, Artificial Intelligence (AI) is progressing from narrow AI to general AI. Narrow AI is aimed at executing specific tasks successfully even at times...

Yuejie Chi – Pittsburgh, PA, United States

A Tale of Preconditioning and Overparameterization in Ill-conditioned Low-rank Estimation
Many problems encountered in science and engineering can be formulated as estimating a low-rank object from incomplete, and possibly corrupted, linear measurements. Through the lens of matrix and...
From Single-agent to Federated Reinforcement Learning
Reinforcement learning (RL) is garnering significant interest in recent years due to its success in a wide variety of modern applications. Q-learning, which seeks to learn the optimal Q-function...
Provable Learning from Data with Priors: from Low-rank to Diffusion Models
Generative priors are effective tools to combat the curse of dimensionality, and enable efficient learning that otherwise will be ill-posed, in data science. This talk starts with the classical...
Statistical Foundations of Reinforcement Learning Through a Non-asymptotic Lens
Reinforcement learning (RL) is garnering significant interest in recent years due to its success in a wide variety of modern applications. However, theoretical understandings on the...

Kenneth W Church – Boston, MA, United States

Better Together: Text + Context
Graph learning has applications in web search (Page Rank), Product Search (Amazon), Biology, Finance and Traffic Analysis for...

Benjamin Richard Cowan – Dublin, Ireland

All too human? Exploring the impact of human-likeness in speech interface design
Speech interfaces are now commonly used through phones, laptops and smartspeakers. Current speech interfaces fundamentally rely on human conversation as an interaction metaphor, using...
Perspective taking, partner models and user behaviour in speech interface interaction
Speech is now a mainstream interaction modality. Design is critical in supporting and informing our perceptions of speech agents as dialogue partners (i.e. our partner models), which are commonly...
Speech Interfaces: Where we are and where we need to be
We now interact with voice interfaces on a daily basis. My talk aims to uncover the main trends in human computer interaction based speech interface research over the past 40 years. It discusses...
Talking my (second) language: How second language speakers interact with voice user interfaces.
Voice user interfaces are now common. Yet not all functionality is afforded to all languages, leaving some users to have to use a second language to engage through voice, or face being excluded...

Rik Das – Ranchi, India

An Image Data based perspective on Data Science, Machine Learning and Deep Learning
Recent times have observed frequent usage of terms like data science, machine learning and deep learning and that too interchangeably in most of the cases. Nevertheless, these terms are...
Is Traditional Image Processing a lost art? : Relevancy check in deep learning era
A surge of deep learning techniques has automated the process of image classification. Traditional techniques of image classification are essentially categorized in two different steps,...
Machine Learning Engineer to Machine Learning Scientist: A journey with Image Processing
This talk bridges the relation between image processing and machine learning. There are numerous youngsters who all are willing to build a career in this particular domain and are...
Machine Learning for non Coders: Your turn to become a ML Expert
This talk has covered the aspects for embracing machine learning by non coders from different backgrounds having a eye for detail. Machine learning is synonymous to modern day craze...

Swagatam Das – Kolkata, India

Do your data behave gently to your Machine Learning algorithms? What if not?
Many machine learning systems rely on implicit assumptions regarding the regularity of data. For instance, several classifiers assume that all classes have an equal number of...
Generative Adversarial Networks - one of the most happening developments in Machine Learning through the lens of Statistics
Generative Adversarial Networks (GANs) represent one of the most significant breakthroughs in deep learning over the past decade. These models consist of two neural networks engaged in a...
Large Language Models and ChatGPT: Statistical and Ethical Perspectives
Large Language Models (LLMs) like ChatGPT have garnered significant attention for their impressive capabilities in natural language understanding and generation. This talk delves into the...
Some Perspectives on Deep Semantic Segmentation of Images with Application to Computer-aided Medical Diagnostics
Semantic segmentation can be conceptualized as a form of pixel-level image classification. The domain has witnessed significant growth, particularly with the advent of deep convolutional...

Kalyanmoy Deb – MI, United States

Machine Learning Assisted Improvements to Multi-Criterion Optimization Algorithms
Multi-criterion optimization problems give rise to a set of Pareto-optimal solutions, which first must be found before a single preferred solution is chosen for implementation. To find a...
Problem Solving with Multiple Criteria ? A New and Innovative Tool in Computing
Most practical search and optimization related problem-solving tasks involve multiple conflicting criteria, which all must be considered simultaneously during an optimization algorithm. A...
Recent Advancements in Evolutionary Multi-Criterion Optimization and Decision-making
Evolutionary multi-criterion optimization (EMO) research is now more than three decades old. Efficient algorithms and demonstrative applications have encouraged researchers...

Gianluca Demartini – Queensland, Australia

Artificial Intelligence with Humans in the Loop
Crowdsourcing is a novel approach used to obtain manual data processing and annotation at scale. This can be used to create Artificial Intelligence systems with humans in the loop that can...

Ilke Demir – Hermosa Beach, CA, United States

Embattling for a Deep Fake Dystopia
Recent advances in the democratization of AI have been enabling the widespread use of generative models, causing the exponential rise of fake content. Nudification of over 680.000 women by...
The Future of Filmmaking: AI for Volumetric Capture and Reconstruction
One picture is worth a thousand words, so what have been told with videos? What about 100 simultaneous videos to reconstruct every frame of life in a 10.000 sq. ft dome? Is it enough to...

Xin Luna Dong – Seattle, WA, United States

Next-generation Intelligent Assistants for Wearable Devices
An intelligent assistant shall be an agent that knows you and the world, can receive your requests or predict your needs, and provide you the right services at the right...
The Journey to a Knowledgeable Assistant
For decades, multiple communities (Database, Information Retrieval, Natural Language Processing, Data Mining, AI) have pursued the mission of providing the right...

Asif Ekbal – Jodhpur, India

Deep Learning for Natural Language Processing
Natural Language Processing (NLP) is one of the most promising areas that encompasses Artificial Intelligence, Linguistics, Cognition, Physics, Mathematics, logic etc. There has...
Deep Learning for Sentiment Analysis
Sentiment Analysis is a well-established task which aims at determining the polarity of opinion expressed in a given user’s review. Most of the existing works focus on discovering sentiments...
Empathetic AI: Teaching Computers Empathy and Politeness
The Conversational AI System, powered by Natural Language Processing (NLP) and Machine Learning has been at the forefront of the Artificial Intelligence (AI) revolution during the last few...
Neural Machine Translation in Low-resource Languages
Machine Translation (MT) is one of the most prominent technologies that bridges the gap between the people, speaking in different languages and are from different geographic origins. India...
Probing hate speech and misinformation detection on the shoulder of affective information and multitask learning
Hate speech and misinformation are two most critical issues in today's world. Moderators often face a double challenge regarding reducing offensive and harmful content in social media....

Kaoutar El Maghraoui – Yorktown Heights, NY, United States

Optimizing Deep Learning for Real-World Deployment: The Role of Hardware-Aware Neural Architecture Search
Hardware-aware Neural Architecture Search (NAS) has emerged as a crucial approach to optimize the design of deep neural networks (DNNs) for specific hardware platforms, unlocking...
Platform for Next-Generation Analog AI Hardware Acceleration
Analog In-Memory Computing (AIMC) is a game-changing approach that boosts the efficiency of Deep Neural Network (DNN) inference and training. It tackles the performance losses caused by...
Powering the Future of Efficient AI through Approximate and Analog In-Memory Computing Principals
Artificial Intelligence has transformed nearly every business process and industry, from finance, healthcare, and energy to supply chain optimization, sales, marketing, and HR. The...
Revolutionizing Enterprise AI: The Power and Promise of Foundation Models
Modern AI models excel at processing vast amounts of data and addressing complex problems through innovative solutions. As we progress, AI is undergoing a transformative shift towards the...

Lance Eliot – Palo Alto, CA, United States

Artificial Intelligence Trends for Computer Science Students
Artificial Intelligence (AI) is a hot topic and offers great opportunities for computer science students. This talk covers the latest key trends in AI and discusses research challenges worthy of...
Career Advice for Computer Science Students
What will you do after completing your computer science degree? Many computer science students are unsure of what they will do next after graduation. There are a multitude of avenues to choose...
Entrepreneurship for Computer Science Students
Computer science students often dream of being an entrepreneur and launching a high-tech startup but do not know what this entails and how to get underway. This talk covers the key elements of...

Bjoern M Eskofier – Erlangen, Germany

AI for Future Healthcare
The fast-growing costs of acute care are pushing the healthcare systems worldwide to a limit. Globally, we are coming to realize that we cannot afford to provide everybody with access to...
Machine Learning: Trends (and Hypes?)
The talk highlights current trends (and hypes?) in machine learning and artificial intelligence. Example projects in the abovementioned domains will be highlighted, as well as basic technology...
Wearable computing systems and machine learning for sports science research
Wearable computing systems play an increasingly important role in recreational and elite sports. They comprise of two parts. First, sensors for physiological (ECG, EMG, ...) and...

João Gama – Porto, Portugal

Current Trends in Learning from Data Streams
Learning from data streams is a hot topic in machine learning and data mining. In this talk, we present three different problems and discuss streaming techniques to solve them. The first problem...
Data Mining for the XXI Century
Nowadays, there are applications where data is best modeled not as persistent tables, but rather as transient data streams. In this talk, we discuss the limitations of current machine learning and...
Evolving Social Networks: trajectories of communities
In recent years we witnessed an impressive advance in the social networks field, which became a ”hot” topic and a focus of considerable attention. The development of methods that focus...

Dan Garcia – Millbrae, CA, United States

Following your passion: Graphics, Game Theory and Genealogy
This talk highlights the work of two "Research, Art, and Development" (RAD) student groups founded by Professor Dan Garcia in 2001, that have been active for almost twenty years. The UC...
GamesCrafters: Solving the World's Board Games with Computational Game Theory
The UC Berkeley GamesCrafters undergraduate research and development group explores the fertile area of combinatorial and computational game theory. While most students implement new games, others...

Nitesh Goyal – Stamford, CT, United States

Impact of Data Annotator Identity on ML Model Outcomes: Unpacking Specialized Rater Pools
Machine learning models are commonly used to detect toxicity in online conversations. These models are trained on datasets annotated by human raters. We explore how raters' self-described...

Sumit Gulwani – Redmond, WA, United States

AI-assisted Programming: Applications, Experiences, and Neuro-symbolic techniques
AI can enhance programming experiences for a diverse set of programmers. This includes professional developers and data scientists who require assistance in software engineering and data...
Art of Disruptive Research
Sumit’s research career, spanning more than 2 decades, has been filled with diverse experiences: from proving theorems to writing code and shipping features inside mass-market...
Enhancing LLM performance with Cognitive Strategies
Large Language Models (LLMs) have emerged as a powerful general-purpose tool capable of performing a wide variety of tasks. However, they are not very precise by themselves. The good news is that...
The Story of Flash Fill and how it shaped me
The Flash Fill feature in Microsoft Excel allows users to automate string transformations like converting “FirstName LastName” to “lastname, firstname” from just one...

Zhu Han – Houston, TX, United States

Distributionally Robust Optimization and Machine Learning for Communication Networks
Recently, distributionally robust optimization theory is introduced to overcome the shortcomings of these two approaches, which assumes that the distribution of the random variable is within an...
Generative AI Enabled Semantic Communication
Semantic communication (SemCom), a prominent feature of 6G, aims to address communication problems at the semantic level by transferring semantic information accurately and efficiently. Advances...
The Transformative Impact of Generative AI: Strategies, Applications, and Innovations
This speech explores the transformative potential of Generative AI (GAI) across various domains. Firstly, we examine the use of Large Language Models (LLMs) in repeated games to develop...

David Howard – Brisbane, QLD, Australia

AI-Based Design of Industrial Components for Next-Gen Industry
Generative machine learning is poised to revolutionise the design of a range of sectors where rational design has long been the de facto approach: where design is practically a time...
Autonomous Soft Robot Design
The emerging field of soft robotics presents a new paradigm for robot design in which “precision through rigidity” is replaced by “cognition through compliance.”...
Embodied Intelligence and Morphological Computing in Robotics
Embodied intelligence is a vital and relevant philosophy that explains the emergence of natural intelligence, as aptly demonstrated by the rich array of flora and fauna in our world. In this...
Robotic Simulation, Modelling, and the Reality Gap
The use of simulators in robotics research is widespread, underpinning the majority of recent advances in the field. There are now more options available to researchers than ever before,...

Longbo Huang – Beijing, China

Designing Efficient and Robust Deep Reinforcement Learning Algorithms
Deep reinforcement learning (DRL) has received much attention and finds successful applications in various important fields, including games, robotics, transportation and science. Despite its...

Rasheed Hussain – Bristol, United Kingdom

Contextual Responsible Artificial Intelligence (AI)
– Artificial Intelligence is omnipresent, and the last few decades have seen revolutionary achievements through AI in almost aspect of life. However, some aspects of the AI have still not...
Friend or Foe: Role of Artificial Intelligence and Machine Learning in Cybersecurity
This lecture covers the role of Artificial Intelligence (AI) in Cybersecurity. With the emergence of new technologies, increase in the volume, velocity, veracity, and variety of data calls for new...
Role of Machine and Deep Learning in IoT security
This lecture covers the role of Artificial Intelligence (AI) in the security of Internet of Things (IoT). With the emergence of new technologies, increase in the volume, velocity, veracity, and...

Letizia Jaccheri – Trondheim, Norway

Artificial Intelligence for All
Software is an infrastructure of all industries and societies around the world,...

Anura Jayasumana – Fort Collins, CO, United States

Machine Learning and Networks - Challenges, Solutions and Tradeoffs
We consider the intersection of networks and machine learning in two contexts. In the first, the data of interest...
Machine Learning and Synthetic Data - Potential and Pitfalls
Machine Learning (ML) models have become indispensable for solving complex problems. However, they require sufficient volumes of representative training data to be...

Latifur Rahman Khan – Plano, TX, United States

MultiCon: A Multi-Contrastive Learning based Semi-Supervised Classification Framework and Its Applications Towards Covid19
Deep neural networks (DNN) require a large number of annotations, which sometimes is very expensive and cumbersome. Over the years, various efforts have been proposed for reducing the annotation...

Irwin King – Hong Kong, Hong Kong

AI Innovations in Education: Exploring Present Trends and Future Directions
Artificial Intelligence (AI) has made a significant impact on education in recent years. This presentation will explore the current landscape of AI in teaching and learning, focusing on...
Graph Neural Networks from Theory to Applications
Graph Neural Network (GNN) is a type of neural network designed to process graph-structured data. This includes data from social networks, citation networks, traffic networks, semantic networks,...
Multimodal Foundation and Large Language Models: Applications, Challenges, and Future Directions
In recent years, the field of artificial intelligence has witnessed significant advancements in multimodal foundation and large language models. This seminar presentation will provide an...
Social Recommendations: A historical perspective and recent advancements
With the exponential growth of information generated on the Internet, social recommendation has been a hot research topic in social computing after the popularization of social media as filtered...
Trustworthy Artificial Intelligence with Federated Learning
Artificial intelligence (AI) has quickly become an integral part of our daily lives, appearing in virtual assistants and...

Manoj Kumar Kumar – Sydney, Australia

Unveiling the Power of Generative AI
In the realm of cutting-edge technology, Generative AI emerges as a formidable force, shaping industries and paving the way for unprecedented innovation. This talk endeavors to demystify...

C.-C. Jay Kuo – Los Angeles, CA, United States

On Sustainable Healthcare and Sustainable AI
This talk addresses two sustainability challenges in our society. The first one is the sustainability of today’s healthcare services. As people’s life is prolonged, the need for...
Toward Interpretable and Sustainable AI
Rapid advances in artificial intelligence (AI) and machine learning (ML) have been attributed to the wide applications of deep learning (DL) technologies. There are, however, concerns with this AI...

Eren Kurshan – New York, NY, United States

Making or Breaking AI: Grand Challenges, Opportunities and What We Might be Missing
Artificial Intelligence solutions face 3 Grand Challenges: (1) The Energy Challenge: An unprecedented growth in the training energy consumption is on the path to becoming ‘the...

Antonio Lieto – Salerno, Italy

Cognitive Heuristics for Commonsense Thinking and Reasoning in the next generation Artificial Intelligence
Commonsense reasoning is one of the main open problems in the field of Artificial Intelligence (AI) while, on the other hand, seems to be a very intuitive and default reasoning mode in humans and...
The Cognitive Paradigm in the Artificial Intelligence Research
In the last decades, the research in Artificial Intelligence (AI) has reached remarkable results in a variety of fields ranging from computer vision to language technologies. Despite these...

David Lo – Singapore, Singapore

Charting New Frontiers: Exploring Limits, Threats, and Ecosystems of LLMs in Software Engineering
Large language models (LLMs) are transforming software engineering, but their adoption brings critical challenges. In this lecture, I will explore three key thrusts: the *limits* of LLMs,...
Efficacy, Efficiency, and Security of Code LLMs: Promises and Perils
Researchers have explored methods to automate software engineering (ASE) tasks for decades. In recent years, we have been excited about the potential of code Large Language Models (code LLMs) for...
Efficient and Green Code LLMs: Happier Software Engineers, Happier Planet
Many have been excited about the potential of code Large Language Models (code LLMs). However, code LLMs are large, slow, and energy-hungry compared to traditional ASE solutions, which...
Requirements Engineering for Trustworthy Human-AI Synergy in Software Engineering 2.0
Software Engineering 2.0 envisions trustworthy and synergistic collaborations between humans and AI agents that are diverse, responsible, and autonomous, aiming to build the software of...
Software Reliability in the Era of Large Language Models: A Dual Perspective
Much software engineering research has been dedicated to building reliable software systems. The last two decades have witnessed the growth of software engineering data availability that spurred...

Seng Loke – Melbourne, VIC, Australia

Cooperative Vehicles: is this the Future of Transport?
The connected automated vehicle holds great promise for revolutionising transport. Advanced technologies including extensive sensing and Artificial Intelligence (AI) algorithms have enabled such...

Walid Maalej – Hamburg, Germany

AI Engineering - How can Software & Requirements Engineering Help Solving the "AI Dilemma"
AI and Software Engineering have co-evolved and profited from each other since their beginnings. During the last decade, Software Engineering has particularly profited from advances in...

A. Cristiano I. Malossi – Rüschlikon, Switzerland

The Future of Visual Inspection for Civil Infrastructure
Until recently bridge inspection was exclusively a manual process conducted by reliability engineers. Not only is this dangerous due to the complexity of the structure, but it is also...

Maja Mataric´ – South Pasadena, CA, United States

Robots That Care: Socially Assistive Robotics and the Future of Work and Care
The nexus of advances in robotics, NLU, and machine learning has created opportunities for personalized robots. The current pandemic has both caused and exposed unprecedented levels of...
Robots That Care: Socially Assistive Robotics for Eldercare
The nexus of advances in robotics, NLU, and machine learning has created opportunities for personalized robots for the various domains of eldercare: aging in place, assisted living, and...
Socially Assistive Robotics Right Now: Personalized Embodied Systems for In-Home Support of Health, Wellness, Education, and Training
The nexus of advances in robotics, natural language processing, and machine learning has created opportunities for personalized robots in a variety of domains of daily life. The current pandemic...
Socially Assistive Robotics as a Path to Accessible Personalized Autism Spectrum Disorder (ASD) Therapy Support
The last decade has seen a convergence of technologies that make it possible for users to interact with intelligent agents in therapeutic settings. Concurrently, much research has been done...

Ujjwal Maulik – Kolkata, India

Artificial Intelligence and Data Science: Current Trends and Future Challenges
In this lecture first we will describe current trends in Artificial Intelligence (AI), and Data Science. In this regard we will demonstrate applications of different machine learning algorithms...
Computational Intelligence for Bioinformatics
In the first part of the lecture we will discuss several Computational Intelligence Algorithm that is used for optimization, machine learning and data mining tasks. This include Genetic...
Machine Learning and Data Science: Fundamental, Challenges and Future
Supervised and unsupervised pattern classification are important Machine Learning techniques which have wide range of applications. While supervised classification techniques use training...
Unsupervised Pattern Classification in Single and Multi-objective Framework
Data clustering is a popular unsupervised pattern classification technique that is used for partitioning a given data set into homogeneous groups based on some similarity/dissimilarity...

Ajmal Saeed Mian – Crawley, WN, Australia

3D Deceptive Textures for Physical World Adversarial Attacks
Deep learning offers state-of-the-art solutions for multiple computer vision tasks. How-ever, deep neural models are vulnerable to slight input perturbations that can significantly change model...
Deep Learning for Multiple Object Tracking
Multiple Object Tracking (MOT) plays an important role in solving many fundamental problems in video analysis. MOT involves object detection followed by object association. While object detection...
Deep Learning over 3D Point Clouds
3D point clouds are becoming an important data source for vision tasks such as auton-omous driving and robotic perception. However, deep learning over unstructured point clouds is challenging. We...
Dense 3D Face Correspondence for Deep 3D Face Recognition and Medical Applications
In this talk, I will present our research on dense 3D face correspondence which is a core problem in facial analysis for many applications such as biometric identification, symptomatology for the...
Learning from Legacy MoCap Data for Precision Modelling of 3D Human Motion for Behavioural and Performance Analysis
Modelling human actions is useful for surveillance, sports and medical applications. State of the art models are based on deep learning from large amounts of annotated data which is expensive to...
Threat of Adversarial Attacks on Deep Learning in Computer Vision
Deep learning is at the heart of the current rise of artificial intelligence. However, deep models are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that make the...

Kenny Mitchell – Burbank, CA, United States

Delivering Intelligence Telexistence in Virtual Worlds with Everyone
This talk presents experiences and thoughtful strategies of delivering research into mass appeal interactive virtual worlds from 3d multiplayer streaming immersion in the rich story worlds of...
Delivering Interactive Emotional Avatars with Everyone
Exploring the evolution of delivering interactive emotional avatars in visual media production industries, through movies and games and beyond, this talk records one experience of how fidelity has...

Peyman Moghadam – Brisbane, QLD, Australia

3D Geometry meets Learning
In this lecture, I will give an overview of current Deep Learning methods for lidar-based place recognition. Place recognition aims to associate input lidar data to a global map or database of...
Self-Supervised and Continual Representation Learning in Unstructured Environments
In today's robotic applications, learning-based methods play a key role in tasks like (re)-localization, perception, navigation, and manipulation. However, these methods...
The Future of Computing in the Era of Embodied Intelligence
We are entering a new era where AI is no longer confined to the cloud, it is becoming embodied AI agents that are learning by...

San Murugesan – Sydney, NSW, Australia

The Rise of Autonomous Systems: Advances, Applications, and Opportunities
Autonomous system revolution has begun. As they make the transition away from stories of science fiction, autonomous systems have become a practical reality and a game changer. They are...
Trust-Worthy and Responsible AI
Artificial intelligence (AI), a novel problem solver and an enabler of disruptive innovations, is permeating everywhere. It is being harnessed in several applications tackling several...

Olfa Nasraoui – Louisville, KY, United States

Explainability and Debiasing by Design in Recommender Systems
At its core, AI is enabled by advanced Machine Learning (ML) models that are now being used increasingly to enable decision making in many sectors, ranging from e-commerce to health,...

Corina Pasareanu – Sunnyvale, CA, United States

Formal Verification and Run-time Monitoring for Learning-Enabled Autonomous Systems
Providing safety guarantees for autonomous systems is difficult as these...

Sudeep Pasricha – Fort Collins, CO, United States

Artificial Intelligence at the Speed of Light
The massive data deluge from mobile, IoT, and edge devices, together with powerful innovations in data science and hardware processing, have established artificial intelligence (AI) as the...

Steven Pemberton – Amsterdam, Netherlands

There's no I in AI (yet)
There's no intelligence in current AI systems, but apparently we think there is, and then get surprised when it gives wrong answers. Why is this, and what will happen when we get...

Junaid Qadir – Doha, Qatar

Adversarial Machine Learning and Vehicular Networks: Strategies for Attack and Robust Defense
Machine learning (ML) has seen a lot of recent success in a wide variety of applications and industries. But despite their great success, researchers have shown that ML algorithms are easy to fool...
Adversarial Machine Learning and Vehicular Networks: Strategies for Attack and Robust Defense
Machine learning (ML) has seen a lot of recent success in a wide variety of applications and industries. But despite their great success, researchers have shown that ML algorithms are easy to fool...
Big Data For Human Development
With the explosion of social media sites and proliferation of digital computing devices and Internet access, massive amounts of public data are being generated on a daily basis. Efficient...
Caveat Emptor: The Risks of Using Big Data for Human Development
"Big Data" has the potential to facilitate sustainable development in many sectors of life such as education, health, agriculture, and in combating humanitarian crises and violent...

Nitendra Rajput – Gurgaon, India

AI in Finance: Need for explainability and trust
The area of Artificial Intelligence has gone through tremendous technological advancement in the past few years. Such advancement means that algorithms are now able to go beyond the lab and...
Temporal Graph Learning for Financial World: Algorithms, Scalability, Explainability & Fairness
The most intuitive way to model a transaction in the financial world is through a Graph. Every transaction can be considered as an edge between two vertices, one of which is the paying...
The Psychology of Deep Learning in Decision Making
In this talk, we will demonstrate that deep learning has a very strong connection to the psychology of human decision making. Several behavioural economists and psychologists have...

Danda B Rawat – Washington, DC, United States

Secure and Trustworthy Machine Learning and Artificial Intelligence for Multi-Domain Applications
Machine Learning (ML) algorithms and Artificial Intelligence (AI) systems have already had an immense impact on our society and have been shown to be able to create machine cognition comparable to...

Sripana Saha – Bihta Patna District, India

AI/ML Applications in Digital Health
In recent years we are working on developing several AI-based assistants to help improve the physical and mental health issues of common people of the society. In order to support telemedicine...
MULTI-MODAL DATA INTEGRATION AND ANALYSIS FOR CANCER PROGNOSIS USING MACHINE LEARNING MODEL
Breast cancer is a concerning disease due to its high incidence and mortality. In recent decades, the incidence and mortality have continuously increased. Its early-stage detection and the...
Multimodal Information Processing: Some recent NLP applications
Multimodal information processing deals with the efficient usage of information available in different modalities such as audio, video, text, etc. for solving various task applications of real...
Multimodal Summarization : Recent Trends and Applications
Large amounts of multi-modal information online make it difficult for users to obtain proper insights. In this talk I will first introduce the concept of multimodal summarization and its various...

KC (Casey) Santosh – SD, United States

#AI for infectious diseases: #Pneumonia, #TB and #Covid-19
AI has contributed a lot to healthcare (AI-based decision-support systems with clinical significance). Infectious disease outbreak is no exception. The talk will provide a walk through about how...

Federica Sarro – London, United Kingdom

MEG: Multi-objective Ensemble Generation
Recent studies have found that ensemble prediction models (i.e., aggregation of multiple base classifiers) can achieve more accurate results than those that would have been obtained by...
Search-based Software Engineering for Modern Software Systems
Realizing modern software systems poses new challenges to the software engineers: Users of applications running on limited capability devices still demand acceptable performance, users of...
Software Fairness
Software Fairness is an emerging property of modern AI-enabled software systems.

Many real-world software is vulnerable to fairness bugs and frequently exhibit unfair...

Nishanth Sastry – London, United Kingdom

Lessons from the age of user-generated content for the age of AI-generated content
The past decade and more has been defined by the rise and near universal adoption of user-generated content (UGC) on social media. Initial excitement about the promise of UGC has since...

Björn Schuller – Munich, Germany

Computer Audition The Era of Large Models
In this lecture, we delve into the fascinating field of Computer Audition Ð that is, hearing, understanding, and generating audio by computers powered by the latest advancements in Artificial...

Abhronil Sengupta – University Park, PA, United States

Neuromorphic Computing: Bridging the gap between Nanoelectronics, Neuroscience and Machine Learning
While research in designing brain-inspired algorithms have attained a stage where such Artificial Intelligence platforms are being able to outperform humans at several cognitive tasks, an...

Yiyu Shi – Notre Dame, IN, United States

Hardware/Software Co-Design Towards Quantum Advantages
Despite the pursuit of quantum advantages in various applications, the power of quantum computers in executing neural network has mostly remained unknown, primarily due to a missing tool that...

Houbing Song – Baltimore, MD, United States

AI for Cybersecurity and Security of AI
The mutual needs and benefits of AI and cybersecurity have been widely recognized. AI techniques are expected to enhance cybersecurity by assisting human system managers with automated monitoring,...
AI/Machine Learning for Internet of Dependable and Controllable Things
The Internet of Things (IoT) has the potential to enable a variety of applications and services. However, it also presents grand challenges in security, safety, and privacy. Therefore, there is a...
Data-Efficient Machine Learning
Most research on machine learning has focused on learning from massive amounts of data resulting in large advancements in machine learning capabilities and applications. However, many...
Real-Time Machine Learning for Quickest Detection
Quickest detection, which refers to real-time detection of abrupt changes in the behavior of an observed signal or time series as quickly as possible after they occur, is essential to enable...
The Third Wave of Artificial Intelligence: Neurosymbolic AI
There are three waves of Artificial Intelligence. The first Wave of AI is Crafted Knowledge, which includes rule-based AI systems. The second wave of AI is Statistical Learning, which includes...

Ram Sriram – Gaithersburg, MD, United States

Transforming Health Care Through Digital Revolutions
Healthcare in the 21st century will be transformed by various digital revolutions. Of particular importance will be four revolutions:...

Mauro Vallati – Huddersfield, United Kingdom

Knowledge Configuration for AI solvers
Given an off-the-shelf solver and a symbolic representation of a problem to be solved, a way for improving performance is the configuration of the parameters of the solver. Such parameters allow...
Knowledge Engineering for AI Planning
Automated Planning is one of the most prominent AI challenges; it has been studied extensively for several decades and led to numerous real-world applications. Recently, Automated Planning...
Planning and Scheduling Approaches for Urban Traffic Control
The current increase in urbanisation, coupled with the socio-economic motivation for increasing mobility, is pushing the transport infrastructure well beyond its capacity. Traditional urban...

Sunil Kumar Vuppala – Bangalore, India

Automation and AI Transformational Journey
The talk covers transformational journey of automation and AI from retrospective to predictive, Role of Machine Learning and Deep learning in intelligent automation, Usage of different...
Computer Vision Overview and Applications
The talk covers overview of computer vision, role of deep learning in computer vision and applications across the industries.
Deep Learning Essentials and Applications
The talk will cover essentials of deep learning - what is deep learning, why is it needed, why the hype now, how deep learning works - forward/backpropagation and where it can be used? The...
Recommendation Systems and Applications

The talk covers overview of recommendation systems, various techniques, evaluation and applications across the industries.
Research problems in Big Data and Data Science
The talk covers introduction of big data and data science, high level research problems in 5 categories: Core Big data area to handle the scale, Handling noise and uncertainty in the data,...

Zhangyang "Atlas" Wang – Austin, TX, United States

Learning to Optimize: A Gentle Introduction
Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand...
Sparse Neural Networks: From Practice to Theory
A sparse neural network (NN) has most of its parameters set to zero and is traditionally considered as the product of NN compression (i.e., pruning). Yet recently,...

Allison Woodruff – Mountain View, CA, United States

Advancing Explainability Through AI Literacy And Design Resources
Explainability helps people understand and interact with the systems that make decisions and inferences about them. This should go beyond providing explanations at the moment of a decision;...
How Knowledge Workers Think Generative AI Will (Not) Transform Their Industries
Generative AI is expected to have transformative effects in multiple knowledge industries. To better understand how knowledge workers expect generative AI may affect their industries in the...

Feng Xia – Melbourne, VIC, Australia

From Data Science to Graph Learning
As data (especially big data) become the new oil, data science has recently attracted intensive and growing attention from industry, government, and academia. Data science focuses on deriving...

Ming Xiao – Stockholm, Sweden

Distributed Machine Learning: Basic and Algorithms
In this talk, we will talk one distributed machine learning (DML) schemes. We start from the introduction of optimization, convex optimization, motivation of distributed machine learning. Then we...
Federated Learning: Algorithms, Analysis and Optimization
In this talk, we will talk about the algorithms of emerging federated learning. We will give the algorithms of Federated Learning. Then, we will explain from mathmetical aspcts on the properties...
Network Coding: Principle, Limits and Applications
In this talk, we will talk about the fundamentals on network coding. We will talk the the basics of network coding (NC) and the fundamental limits of NC. Then, the algebraic methods of NC will be...

Xing Xie – BEIJINGSHI, China

Societal AI: Tackling AI Challenges with Social Science Insights
With the widespread application of artificial intelligence globally, its impact across various fields is becoming increasingly prominent. We advocate for the development...

Elad Yom-Tov – Hoshaya, Israel

Crowdsourced Health: How what you do on the internet will improve medicine
The majority of Internet users report that they search the web for information on their medical concerns. Data generated during this process have proven to be a fruitful source for medical...

Daron Yondem – Istanbul, Türkiye

Agentic LLM Workflows with AutoGen
In the era of artificial intelligence, Large Language Models (LLMs) have catalyzed a transformative shift across multiple domains, heralding a new age of computational ingenuity and...
Mastering Prompt Engineering Techniques
This session provides an in-depth exploration of prompt engineering techniques with recent large language models. A comprehensive walkthrough of various prompt engineering strategies are...
Meet my AI Sidekick!
It has been a long time since we have access to LLMs. I have been playing with it not only for customers but for myself as well. How could I increase my own productivity? What value could I...

Dong Yu – Bothell, WA, United States

Audio/Speech Enhancement and Separation
We have seen significant progress in audio and speech processing in the past several years. In this talk, I will introduce a series of techniques we developed on...

Justin Zobel – Melbourne, VIC, Australia

Smoke or mirrors: A perspective on emerging AIs
AI technologies seem to be poised to disrupt a huge range of industries and activities. The abrupt rise in awareness of AI, following the appearance of publicly available generative tools...