|
Seminars and Events
|
| November 21, 2025 |
-
Title: From Statistical Physics to Privacy: Phase Transitions, Sampling and Differential Privacy
Time: 10:30am
Venue: CB 308
Speaker(s): Prof. Jingcheng Liu
Remark(s): Abstract
Classical interacting particle systems studied in statistical physics are intimately connected to constraint satisfaction problems studied in computer science. Much progress has been made in the recent decade in understanding the "computational" phase transition in Gibbs sampling, where a sharp transition in computational tractability coincides precisely with the underlying physical phase transition in many models. I'll give a survey of my research along this line, and also highlight how these developments also lead to new perspectives and applications in differentially private optimizations.
About the speaker
Jingcheng Liu is an Associate Professor in the Theory Group of the School of Computer Science at Nanjing University. He is broadly interested in theoretical computer science, which includes randomized algorithms, computational phase transition, and differential privacy. Before that, he completed undergrad at SJTU (ACM Honors class) and PhD at UC Berkeley, and he was a Wally Baer and Jeri Weiss postdoctoral scholar at Caltech.
|
| November 20, 2025 |
-
Title: The Wild Robot: A Journey Toward Long-Horizon Agentic Intelligence
Time: 11:00am
Venue: HW312, Haking Wong Building
Speaker(s): Prof. Ivor W Tsang
Remark(s): Abstract
Long-horizon planning in robotic manipulation demands translating abstract goals into precise, executable actions while maintaining spatial, temporal, and physical consistency. However,
language model-based planners often fail to handle extended task decomposition, constraint satisfaction, and adaptive recovery from errors. We present The Wild Robot, a framework for autonomous, feedback-driven reasoning that constructs and refines symbolic instruction graphs to guide code generation in robotic tasks. The system dynamically decomposes complex goals into coherent subtasks and generates executable control programs accordingly. When execution failures occur, it analyzes environmental feedback to induce and propagate new constraints, enabling targeted refinement without restarting the planning process. This structured, interpretable approach fosters resilience, adaptability, and transparency, significantly enhancing performance in long-horizon and constraint-sensitive robotic benchmarks. The Wild Robot represents a step toward truly agentic intelligence capable of robust, self-correcting decision-making in complex, real-world manipulation scenarios.
About the speaker
Professor Ivor W. Tsang is the Director of the A*STAR Centre for Frontier AI Research (CFAR) and an Adjunct Professor at the College of Computing and Data Science, NTU, Singapore. Since January 2022, he has led Singapore’s national initiative on Trustworthy Foundation Models under the National Multimodal LLM Programme. He also drives research on Agentic World Models and oversees major national initiatives such as the AI Singapore Materials Design Grand Challenge and the Maritime AI Programme. Under his leadership, CFAR has secured over S$23 million in strategic research funding, strengthening Singapore’s frontier AI ecosystem.
His research spans transfer learning, deep generative models, and big data analytics involving ultra–high-dimensional data. His influential work has earned international recognition, including the ARC Future Fellowship (2013), the ICCM Best Paper Award (2019), and recognition as the AI 2000 AAAI/IJCAI Most Influential Scholar in Australia (2020). An IEEE Fellow, he has made distinguished contributions to large-scale and transfer learning. He also serves on editorial boards of leading AI journals and top AI conference committees.
|
| November 19, 2025 |
-
Title: Recent Advances in Game-Theoretic Feature Attributions for Kernel Methods and Gaussian Processes
Time: 02:30pm
Venue: Room 301, Run Run Shaw Building
Speaker(s): Prof. Siu Lun Chau
Remark(s): Abstract
Kernel methods and Gaussian processes are powerful nonparametric learning frameworks grounded in positive definite kernels. Yet, their flexible black-box nature often comes at the cost of interpretability. This seminar presents recent advances in game-theoretic feature attribution for kernel methods and Gaussian processes, bridging cooperative game theory with kernel-based learning. I will discuss how these methods offer principled and computationally tractable attributions—reducing the exponential complexity of Shapley value estimation to polynomial time—and how they naturally extend to explain not only predictions, but also distributional discrepancies, dependency measures, and predictive uncertainty.
About the speaker
Siu Lun Chau is an Assistant Professor in Statistical Machine Learning at Nanyang Technological University, Singapore. His research focuses on understanding and addressing epistemic uncertainty in machine learning—how to represent, quantify, propagate, compare, and explain knowledge-level uncertainty in intelligent systems. Before joining NTU, he was a Postdoctoral Researcher at the CISPA Helmholtz Center for Information Security with Dr. Krikamol Muandet and obtained his DPhil in Statistics from the University of Oxford under the supervision of Prof. Dino Sejdinovic. His work has been recognised with the IJAR Young Researcher Award for contributions at the intersection of imprecise probability theory and machine learning.
-
Title: Deep Model Fusion
Time: 10:00am
Venue: HW312, Haking Wong Building
Speaker(s): Prof. Dacheng Tao
Remark(s): Abstract
In recent years, we have witnessed a profound transformation in the learning paradigm of deep neural networks, especially in the applications of large language models and other foundation models. While conventional deep learning methodologies maintain their significance, they are now augmented by emergent model-centric approaches such as transferring knowledge, editing models, fusing models, or leveraging unlabelled data to tune models. Among these advances, deep model fusion techniques have demonstrated particular efficacy in boosting model performance, accelerating training, and mitigating the dependency on annotated datasets. Nevertheless, substantial challenges persist in the research and application of effective fusion methodologies and their scalability to large-scale foundation models. In this talk, we systematically present the recent advances in deep model fusion techniques. We provide a comprehensive taxonomical framework for categorizing existing model fusion approaches, and introduce our recent developments, including (1) weight learning-based model fusion and data-adaptive MoE upscaling, (2) subspace learning approaches to model fusion, and (3) enhanced multi-task model fusion incorporating pre- and post-finetuning to minimize representation bias between the merged model and task-specific models.
About the speaker
Prof. Dacheng Tao is the Distinguished University Professor and the Inaugural Director of the Generative AI Lab in the College of Computing and Data Science at Nanyang Technological University. He was an Australian Laureate Fellow and the founding director of the Sydney AI Centre at the University of Sydney, the inaugural director of JD Explore Academy and senior vice president at JD.com, and the chief AI scientist at UBTECH Robotics. He mainly applies statistics and mathematics to artificial intelligence, and his research is detailed in one monograph and over 300 publications. His publications have been cited over 160K times and he has an h-index 180+ in Google Scholar. He received the 2015 and 2020 Australian Eureka Prize, the 2018 IEEE ICDM Research Contributions Award, 2020 research super star by The Australian, the 2019 Diploma of The Polish Neural Network Society, and the 2021 IEEE Computer Society McCluskey Technical Achievement Award. He is a Fellow of the Australian Academy of Science, ACM and IEEE.
|
| November 18, 2025 |
-
Title: Statistics-Powered AI
Time: 10:30am
Venue: Room 301, 3/F, Run Run Shaw Building
Speaker(s): Prof. Chengchun Shi
Remark(s): Abstract
We have definitely entered an era of generative artificial intelligence (AI), where large language models (LLMs) are increasingly reshaping our daily lives. Their impact is everywhere -- from education and academia to professional work and everyday life. In this talk, I will present two recent NeurIPS papers on statistics-powered AI, focusing on how statistical methodologies can enhance AI's performance in (1) aligning LLM's model outputs with human feedback, and (2) detecting LLM-generated content with rigorous guarantees. Open-source Python implementations are available at https://github.com/Mamba413/AdaDetectGPT and https://github.com/DRPO4LLM/DRPO4LLM.
|
| November 14, 2025 |
-
Title: Task-Driven Image Restoration: Why, How, and What?
Time: 03:00pm
Venue: HW312, Haking Wong Building
Speaker(s): Prof. Kyoung Mu Lee
Remark(s): Abstract
Image degradation is common in real-world scenarios due to factors such as transmission loss, limited camera capability, or poor shooting conditions. These issues often remove key high-frequency details, causing major performance drops in high-level vision tasks like classification, segmentation, and detection. Image restoration (IR) seeks to recover lost details in low-quality images using learned natural image priors, offering a potential solution to this problem. However, studies show that simply applying IR as a preprocessing step rarely restores the information most relevant to high-level tasks. This insight has led to Task-driven Image Restoration (TDIR), which focuses on enhancing visual quality in ways that directly benefit downstream vision tasks. In this talk, we will discuss the key challenges in TDIR and highlight several recent, efficient approaches to address them.
About the speaker
Kyoung Mu Lee (Fellow, IEEE) is currently the Editor-in-Chief (EiC) of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI); He is a distinguished professor at Seoul National University (SNU). He was the founding director of the Interdisciplinary Graduate Program in SNU. He is an Advisory Board Member of the Computer Vision Foundation (CVF). He was a Distinguished Lecturer of the Asia-Pacific Signal and Information Processing Association (APSIPA), from 2012 to 2013. He has received several awards, in particular, the Medal of Merit and the Scientist of Engineers of the Month Award from the Korean Government, in 2018 and 2020, respectively; the Most Influential Paper Over the Decade Award by the IAPR Machine Vision Application, in 2009; the ACCV Honorable Mention Award, in 2007; the Okawa Foundation Research Grant Award, in 2006, and the SNU Excellence in Research Award in 2020. He has also served as a General Chair for ICCV2019, ACMMM2018, and ACCV2018; and an Area Chair for CVPR, ICCV, and ECCV many times. He is the founding member and served as the President of the Korean Computer Vision Society (KCVS). Prof. Lee is a Fellow of IEEE, a member of the Korean Academy of Science and Technology (KAST) and the National Academy of Engineering of Korea (NAEK).
-
Title: Radio Sensing for Human Sensing
Time: 10:30am
Venue: CB 308
Speaker(s): Prof. Stephan Sigg
Remark(s): Abstract
Radio sensing has seen significant advances over the recent decade. I will provide an overview of recent advances, open challenges and new research opportunities. Particularly, as the technology is increasingly integrated with communication platforms, a ubiquitous, connected sensing system is possible. But will such a system indeed be anticipated, given its privacy, ethical and still also technical challenges? On the other hand, new advances towards Quantum RF sensing have been proposed as well as the integration into medical devices and the perception of sentiment, while holographic sensing techniques promise unprecedented imaging capabilities.
About the speaker
Stephan Sigg is a Professor at Aalto University in the Department of Information and Communications Engineering. With a background in the design, analysis and optimisation of algorithms for distributed and ubiquitous systems, he focuses on sensing systems for environmental perception and Usable (perception-based) Security. Especially, his work covers proactive computing, distributed adaptive beamforming, context-based secure key generation and device-free passive activity recognition. Stephan is an editor for the Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT). He has served on the organizing and technical committees numerous prestigious conferences including IEEE PerCom, ACM Ubicomp, IEEE ICDCS.
|
| November 11, 2025 |
-
Title: Manifold Fitting
Time: 10:30am
Venue: Room 301, 3/F, Run Run Shaw Building
Speaker(s): Prof. Zhigang Yao
Remark(s): 
|
| November 10, 2025 |
-
Title: Exploring Synergies in Wireless Systems and Soft Robots
Time: 11:30am
Venue: CB 308
Speaker(s): Mr. Yiwen Song
Remark(s): Abstract
We present our explorations in how advances in wireless systems can offer new opportunities for soft robots, and vice versa. While soft robots grant applications in narrow fields or under intensive human interaction, the robots are powered by on-board batteries, tethered wires, magnetic fields, or lasers, which restrain their mobility in non-line-of-sight, mobile applications. Our work first brings frequency-selective actuation of liquid crystalline elastomer-based soft robots with radio frequency power, through a combined design of soft materials and wireless frontend. We also explore how soft robots can bring capabilities to wireless communication and power delivery by demonstrating waveguide for tumor-treating-field delivery and soft actuatable antennas that automatically reconfigures operating frequencies for software-defined radios. The talk also covers our wireless infrastructure: sensing and programming wireless environment. We show compressed sensing for probing wireless environments and controlling wireless heating inside a microwave oven with frequency-selective surfaces.
About the speaker
Yiwen Song is a fifth-year Ph.D. student at the Department of Electrical and Computer Engineering, Carnegie Mellon University. His advisor is Swarun Kumar. His research spans broadly in wireless systems, including communication, sensing, and powering, and he is specifically interested in the intersection between wireless systems, soft materials, and robotics. He has published more than 10 papers in top-tier venues including Nature Communications, MobiCom, MobiHoc, ICRA, etc.
|
| November 07, 2025 |
-
Title: Measuring and Mitigating Adversarial Intermediaries on the Global Internet
Time: 10:30am
Venue: CB 308
Speaker(s): Dr. Diwen Xue
Remark(s): Abstract
Over the past decade, significant shifts in the threat landscape have positioned network infrastructure itself as a potential adversary. Rapid advances and commoditization of networking technologies such as Deep Packet Inspection (DPI), combined with loosened regulations like the repeal of net neutrality, have granted the network with unprecedented capability and freedom to inspect, modify, throttle, or even hijacks the traffic it transports at fine granularity and line rate. What were once neutral “dumb pipes” have evolved into capable and sometimes adversarial network intermediaries—ranging from malicious middleboxes and rogue ISPs to compromised routers and untrusted transit networks—all creating new threats that increasingly erode user privacy, autonomy, and overall trust in connectivity.
My research seeks to address this shifting threat landscape by building the next generation of secure and private network ecosystems. This vision is grounded in two complementary efforts: (1) empirically modeling how adversarial intermediaries behave today and how they might evolve in the future, and (2) developing principled countermeasures that are sound in theory and deployable at scale. In this talk, I will present a series of measurements and security protocol designs that illustrate this dual approach, with the goal of safeguarding users’ communication on this increasingly adversarial Internet.
About the speaker
Diwen Xue is currently a Research Fellow at the University of Michigan. His research focuses on areas where the privacy, security and availability implications of networked systems affect users in the real world. He conducts Internet measurements at scale, uses those observations to refine threat models, and builds countermeasures to safeguard users’ communication on this increasingly adversarial Internet. Diwen's work has been recognized with several honors, including the Internet Defense Prize, USENIX Security Distinguished Paper, and first place in the CSAW Applied Research Competition. Previously, he completed his Ph.D. at the University of Michigan and his B.A. at New York University.
|
