AI Tea Talks Singapore

Jingzhao Zhang is an assistant professor at Tsinghua, IIIS. He graduated in 2022 from MIT EECS PhD program under the supervision of Prof. Ali Jadbabaie and Prof. Suvrit Sra. His research focused on providing theoretical analyses to practical large-scale algorithms. He now aims to propose theory that are simple and can predict experiment observations. Jingzhao Zhang is also interested in machine learning applications, specifically those involving dynamical system formulations. He received Ernst A. Guillemin SM Thesis Award and George M. Sprowls PhD Thesis Award.

Statistical learning has been a foundational framework for understanding machine learning and deep learning models, offering key insights into generalization and optimization. However, the pretraining-alignment paradigm of Large Language Models (LLMs) introduces new challenges. Specifically, (a) their error rates do not fit conventional parametric or nonparametric regimes and exhibit dataset-size dependence, and (b) the training and testing tasks can differ significantly, complicating generalization. In this talk, we propose new learning frameworks to address these challenges. Our analysis highlights three key insights: the necessity of data-dependent generalization analysis, the role of sparse sequential dependence in language learning, and the importance of autoregressive compositionality in enabling LLMs to generalize to unseen tasks.

Link to participate: https://nus-sg.zoom.us/j/89576036030

Webinar ID: 895 7603 6030

Open to ALL interested in AI

Prateek Prasanna is an Assistant Professor in the Biomedical Informatics department at Stony Brook University, New York. He directs the Imaging Informatics for Precision Medicine (IMAGINE) Lab. His research interests lie at the intersection of medical image analysis and machine learning. He obtained his PhD in biomedical engineering from Case Western Reserve University (CWRU), his masters degree in Electrical and Computer Engineering from Rutgers University, NJ, USA, and bachelors degree in Electrical and Electronics Engineering from National Institute of Technology, Calicut, India.

The effectiveness of diagnostic and prognostic tools is frequently determined by the accurate and timely analysis of imaging presentations. The efficacy of these techniques greatly hinges on an extensive corpus of high volume and properly labeled training data. In practice, especially in biomedical contexts, the gathering of labeled data can be cost-prohibitive and time-consuming. The dependency on diverse, high-quality datasets substantially limits model applicability in complex real-world scenes where data is usually imperfect. More importantly, integration of auxiliary information in the form of clinical input is sub-optimal. In this presentation, we will discuss our research efforts in developing computational imaging biomarkers and clinician-in-the-loop frameworks for precision medicine in real clinical scenarios involving imperfect data. We will cover a spectrum of computational techniques grounded in both biological and domain-specific insights that facilitate the early detection and evaluation of treatment responses across various diseases. These reality-centric features and methods, inspired by the expertise of clinicians provide a comprehensive understanding of the systemic nature of diseases, thereby establishing a foundation for enhancing clinical decision-making paradigms in radiology and pathology.

TBD

Dr. Yue Zhao is an Assistant Professor of Computer Science at the University of Southern California and a faculty member of the USC Machine Learning Center. He leads the FORTIS Lab (Foundations Of Robust Trustworthy Intelligent Systems), where his research addresses three connected levels: ensuring robust and trustworthy AI principles, applying structured and generative AI methods for scientific and societal applications, and developing scalable, open-source AI systems. His work applies to healthcare, finance, molecular science, and political science. Dr. Zhao has authored over 50 papers in top-tier venues and is recognized for his open-source contributions, including PyOD, PyGOD, TDC, and TrustLLM, which collectively have over 20,000 GitHub stars and 25 million downloads. His projects have been used by well-known organizations such as NASA, Morgan Stanley, and the U.S. Senate Committee on Homeland Security & Governmental Affairs. Dr. Zhao has received numerous awards, including the Capital One Research Awards, AAAI New Faculty Highlights Award, Google Cloud Research Innovators, Norton Fellowship, Meta AI4AI Research Award, and the CMU Presidential Fellowship. He also serves as an associate editor for IEEE Transactions on Neural Networks and Learning Systems (TNNLS), an action editor for the Journal of Data-centric Machine Learning Research (DMLR), and as an area chair for leading machine learning conferences.

In this talk, we will explore the challenges and advancements in outlier and out-of-distribution detection, which are critical for building robust AI systems. We will discuss various techniques and frameworks that have been developed to address these challenges, focusing on their applications in real-world scenarios.

TBD

TBD

How does the internal computation of a machine learning model transform inputs into predictions? In this paper, we introduce a task called component modeling that aims to address this question. The goal of component modeling is to decompose an ML model's prediction in terms of its components—simple functions (e.g., convolution filters, attention heads) that are the "building blocks" of model computation. We focus on a special case of this task, component attribution, where the goal is to estimate the counterfactual impact of individual components on a given prediction. We then present COAR, a scalable algorithm for estimating component attributions; we demonstrate its effectiveness across models, datasets, and modalities. Finally, we show that component attributions estimated with COAR directly enable model editing across five tasks, namely: fixing model errors, "forgetting" specific classes, boosting subpopulation robustness, localizing backdoor attacks, and improving robustness to typographic attacks. We provide code for COAR at https://github.com/MadryLab/modelcomponents.

Youtube: https://www.youtube.com/watch?v=PV2ISS_nbfg

Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the potential to address these limitations due to its versatility in interpreting different data types and generating tailored outputs for diverse needs. However, existing biomedical generalist AI solutions are typically heavyweight and closed source to researchers, practitioners and patients. In this talk, We will discuss the development and performance of BiomedGPT, a novel open-source, lightweight vision-language foundation model designed as a generalist AI for biomedical applications. Unlike previous solutions, BiomedGPT is both computationally efficient and accessible, achieving state-of-the-art results in 16 out of 25 benchmarks across a variety of tasks. We will present human evaluation results that underscore its effectiveness in radiology visual question answering, report generation, and summarization, with performance metrics nearing human expert levels. This talk will explore how BiomedGPT exemplifies the potential of a multi-modal, generalist approach to revolutionize medical diagnostics and improve workflow efficiency./p>

Youtube: https://www.youtube.com/watch?v=GexeUn5Dn2I

Dr. Zhang is currently leading the Cognitive Computational Neuroscience and Brain Imaging Group at the School of Psychology and Shanghai Mental Health Center at Shanghai Jiao Tong. Dr. Zhang has long been working at the intersection of brain science and brain-like intelligence. His research primarily focuses on the neural computational mechanisms of the human brain and artificial intelligence by combining psychophysics, Bayesian probabilistic modeling, deep learning modeling, neuromodulation, and functional magnetic resonance imaging. He has published several cognitive neuroscience papers in PNAS, eLife, J Neurosci, Neuroimage, PLoS Comput Biol, etc. Dr. Zhang's research on brain-like computation has also been published in the world's top machine learning conferences (ICML and IJCAI). He is also a reviewer for several brain science journals such as eLife, Cerebral Cortex, and machine learning conferences such as ICML, NeurIPS, IJCAI, ICLR, CVPR, etc. He is also the Area Chair of NeurIPS 2024.

The past decade has seen a surge in the use of sophisticated AI models to reverse-engineer the human mind and behavior. This NeuroAI approach has dramatically promoted interdisciplinary research between neuroscience and AI. This talk focuses on using the neuroAI approach to elucidate human learning mechanisms. The talk will consist of two parts. First, I will present our work on the relationships between the primate visual system and artificial visual systems (i.e., deep neural networks) during the learning of simple visual discrimination tasks. Our deep learning models of biological visual learning successfully reproduce a wide range of neural phenomena observed in the primate visual system during perceptual learning. The novel predictions generated by our models are further validated against multivariate neuroimaging data in humans and multi-electrode recording data in macaques. In the second part, I will discuss our recent work on neural and computational mechanisms of how the human brain mitigates catastrophic forgetting during continual multitask learning. Leveraging neural network modeling on human learning behavior, we show that the human brain directly distills learned knowledge via elastic weight consolidation rather than other methods such as memory replay. These studies have profound implications for interdisciplinary research at the intersection of neuroscience and artificial intelligence.

Youtube: https://www.youtube.com/watch?v=vZC8RmnsGqo

Alex Lamb is a senior researcher in the AI Frontiers group at Microsoft. He completed his PhD under Yoshua Bengio and has worked on deep learning, generative models, reinforcement learning, and sequence models. He also worked on deep learning for classical Japanese document recognition as well as demand forecasting systems at Amazon.

Generative AI has led to stunning successes in recent years but is fundamentally limited by the amount of data available. This is especially limiting in the embodied setting – where an agent must solve new tasks in new environments. In this talk, I'll introduce the idea of compositional generative modeling, which enables generalization beyond the training data by building complex generative models from smaller constituents. I'll first introduce the idea of energy-based models and illustrate how they enable compositional generative modeling. I'll then illustrate how such compositional models enable us to synthesize complex plans for unseen tasks at inference time. Finally, I'll show how such compositionality can be applied to multiple foundation models trained on various forms of Internet data, enabling us to construct decision-making systems that can hierarchically zero-shot manner.

Youtube: https://youtu.be/qJyy21-LPQY

Yilun Du is an incoming Assistant Professor at Harvard, starting in Fall 2025 at the Kempner Institute and Computer Science department. He is a final year PhD student in EECS at MIT, advised by Prof. Leslie Kaelbling, Prof. Tomas Lozano-Perez, and Prof. Joshua B. Tenenbaum. Yilun's research focuses on generative models, decision making, robot learning, and embodied agents. His work addresses the challenges of limited decision-making data and generalization to unseen situations using energy landscapes for composable generative models. Yilun aims to develop a decentralized generative architecture for decision-making and enhance models with reinforcement learning, with applications in fields like computational biology.

Generative AI has led to stunning successes in recent years but is fundamentally limited by the amount of data available. This is especially limiting in the embodied setting – where an agent must solve new tasks in new environments. In this talk, I'll introduce the idea of compositional generative modeling, which enables generalization beyond the training data by building complex generative models from smaller constituents. I'll first introduce the idea of energy-based models and illustrate how they enable compositional generative modeling. I'll then illustrate how such compositional models enable us to synthesize complex plans for unseen tasks at inference time. Finally, I'll show how such compositionality can be applied to multiple foundation models trained on various forms of Internet data, enabling us to construct decision-making systems that can hierarchically zero-shot manner.

Youtube: https://youtu.be/qJyy21-LPQY

Baifeng Shi is a Ph.D. student advised by Prof. Trevor Darrell at UC Berkeley. He previously graduated from Peking University with a B.S. degree in computer science. Baifeng's research focuses on building generalist vision and robotic models.

Larger models, more data, and longer training are the three-pronged approaches to scaling up visual pre-training. In this talk, I will first share our recent work that challenges the necessity of larger models. We find that pre-trained and frozen smaller models run on larger image scales (e.g., 224->448->672) are generally better than larger models (e.g., Base->Large->Giant). This trend holds across a variety of vision tasks—including image classification, semantic segmentation, and depth estimation—as well as Multimodal LLM benchmarks and robotic tasks. We demonstrate that smaller models, when pre-trained on multiple image scales, have similar model capacities as larger models and can perform on par or even better. Next, I will share some thoughts on the future of scaling visual pre-training, specifically, whether we should shift our focus from larger models to larger images, and how to utilize bottom-up and top-down attention to scale to extremely large images without hitting the computational constraints.

Youtube: https://youtu.be/oULYfb0sc30

Natasha Jaques is an Assistant Professor of Computer Science and Engineering at the University of Washington, and a Senior Research Scientist at Google DeepMind. Her research focuses on Social Reinforcement Learning in multi-agent and human-AI interactions. During her PhD at MIT, she developed techniques for learning from human feedback signals to train language models which were later built on by OpenAI's series of work on Reinforcement Learning from Human Feedback (RLHF). In the multi-agent space, she has developed techniques for improving coordination through the optimization of social influence, and adversarial environment generation for improving the robustness of RL agents. Her work has received various awards, including Best Demo at NeurIPS, an honourable mention for Best Paper at ICML, and the Outstanding PhD Dissertation Award from the Association for the Advancement of Affective Computing. Her work has been featured in Science Magazine, MIT Technology Review, Quartz, IEEE Spectrum, Boston Magazine, and on CBC radio. Natasha earned her Masters degree from the University of British Columbia, and undergraduate degrees in Computer Science and Psychology from the University of Regina.

Fine-tuning language models with reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models to human values. This talk will give a tutorial on RLHF, diving into the details of how to actually perform RL-finetuning of language models. I will cover the history of innovations leading to the form of RLHF used in ChatGPT, including my own work on KL-regularized RL fine-tuning of language models and human-centric dialog training, as well as OpenAI's early work on learning from human preferences with deep RL. Putting it all together, we will see how what has become known as RLHF integrates these techniques. We will then briefly cover recent developments and directions for future work.

Youtube: https://www.youtube.com/watch?v=VOgrYxFe-r0