Events

Oct 26 - Nov 1, 2025

• 

  BiCoLoR: Communication-Efficient Optimization with Bidirectional Compression and Local Training

  Laurent Condat, Senior Research Scientist, Computer Science

  Oct 27, 12:00 - 13:00

  B9 L2 R2325

  optimization Distributed algorithms Signal and Image Processing

  We introduce BiCoLoR, the first algorithm to combine local training with bidirectional compression using arbitrary unbiased compressors, achieving accelerated complexity and demonstrating superior empirical performance.
• 

  Collective Behaviors - From Traffic Congestion to Chase-and-Escape

  Toru Ohira, Professor, Dean of the Graduate School of Mathematics, Nagoya University, Japan

  Oct 26, 14:30 - 15:30

  B5 L5 R5220

  Mathematical modeling

  In this lecture, we introduce representative mathematical models of collective motion, showing how they capture unexpected emergent patterns and discuss chase-and-escape dynamics, a classic topic in mathematical modeling.
• 

  Integrated Silicon Photonics with Quantum Dot On-Chip Lasers

  Yating Wan, Assistant Professor, Electrical and Computer Engineering

  Oct 26, 12:00 - 13:00

  B9, L2, R2325

  Integrated silicon photonic has emerged as a leading solution for scalable, power-efficient, and environmentally friendly applications. This talk will focus on the prospects and applications of on-chip lasers, a critical component driving the advancement of photonic integrated circuits (PICs). We will discuss various approaches to integrating lasers on silicon and their applications in optical communication, computing, and LiDAR, with a particular emphasis on heterogeneous integration of quantum dot (QD) lasers. QD lasers offer unique advantages, including high immunity to reflection, superior thermal stability, low threshold, and long-term reliability, making them ideal for high-speed optical interconnects, AI-driven computing, and quantum photonic systems. By leveraging the defect tolerance and temperature resilience of QDs, we achieve high-performance, energy-efficient integration with silicon photonics. This talk will highlight recent breakthroughs in QD-on-silicon integration, performance optimizations, and future directions toward heterogeneous photonic systems, paving the way for a new generation of high-speed, low-energy, and scalable optical circuits for next-generation applications.

Oct 19 - Oct 25, 2025

• 

  A Generalized Gaussian Min–Max Framework Inferring Post-Processing Effects in High-Dimensional Estimation

  Abla Kammoun, Senior Research Scientist, Electrical and Computer Engineering

  Oct 21, 14:30 - 15:30

  B1 L3 R3119

  statistical analysis

  This talk introduces the Convex Gaussian Min–Max Theorem (CGMT) as a principled framework to analyze the performance of such solutions, and presents a new Gordon-type inequality to study functionals of the solutions that arise when direct deployment is infeasible.
• 

  One-on-One Statistical Consulting for KAUST Researchers 2025

  Oct 20, All day

  B1 L4 R4102

  In recognition of World Statistics Day, a United Nations–designated observance that highlights the importance of trustworthy data and sound statistical methods, the KAUST Student Chapter of the American Statistical Association (ASA) is hosting one-on-one consulting sessions for KAUST students and researchers. Graduate students and postdoctoral researchers from the Statistics Program will be available to provide personalized guidance on research-related statistical challenges. These consultations aim to strengthen the use of statistical methods across disciplines, support high-quality research

Oct 12 - Oct 18, 2025

• 

  Bias-Reduced Estimation of Structural Equations Models

  Haziq Jamil, Research Specialist, Statistics

  Oct 16, 12:00 - 13:00

  B9 L2 R2325

  This talk demonstrates that the reduced-bias M-estimation (RBM) framework is a computationally efficient and robust method for mitigating finite-sample bias in structural equation models, outperforming standard estimators, especially in small-sample contexts.
• 

  Learning-Based Observer Design for Nonlinear Systems with Convergence Guarantees

  Yasmine Marani, Ph.D. Student, Electrical and Computer Engineering

  Oct 14, 10:00 - 12:00

  B3 L5 R5220

  This thesis advances nonlinear estimation by proposing learning-based nonlinear observers with convergence guarantees. The proposed approaches overcome the limitations of the existing methods by being applicable to a wide range of nonlinear systems while providing global convergence guarantees. Furthermore, the developed observers are robust to disturbances, sensor delay, and measurement noise.
• 

  KAUST Robotics Bay Inauguration

  Oct 13, 14:00 - 15:30

  B5 L2 R2800

  robotics autonomous systems Mechatronics Multi-agent systems

  Join us for the Robotics Bay inauguration at KAUST.
• 

  Bio-Inspired Consensus Enabledby Distributed Active Perception

  Fumin Zhang, Chair Professor and Director, Cheng Kar-Shun Robotics Institute, Hong Kong University of Science and Technology

  Oct 13, 12:00 - 13:00

  Auditorium (between Buildings 4 and 5), Level 0, Room 0215

  Consensus is a fundamental requirement for coordination and cooperation among a swarm of intelligent agents. In environments with difficulty for localization and communication, achieving swarm level consensus is a challenging task. We propose a layered approach to achieve signal propagation over large swarms through active perception. Biological evidence from fish swarms has shown that distributed active perception is used by animals to allow fast response to stimulations when only a few members are excited.
• 

  Phase-Change Memory for In-Memory Computing

  Ghazi Sarwat Syed, Research Staff Member, IBM Research, Switzerland

  Oct 12, 12:00 - 13:00

  B9, L2, R2325

  This talk, structured as a tutorial, will elucidate the core principles of In-memory computing (IMC), showing how the physical properties and inherent organization of memory devices can help overcome the limitations of conventional data processing architectures.

Oct 5 - Oct 11, 2025

• 

  Block Low-Rank Matrices for Modern Scientific Computing

  Daria Sushnikova, Postdoctoral Research Fellow, Computer, Electrical and Mathematical Sciences and Engineering

  Oct 9, 12:00 - 13:00

  B9 L2 R2325

  Block low-rank matrices provide framework for compressing and accelerating large-scale computations. In this talk, I will introduce the basic principles behind these matrix formats, highlight notable algorithms that exploit their structure, and discuss their growing role in modern computational mathematics. Applications ranging from seismic imaging and computational biology to artificial intelligence will be used to illustrate the broad impact of block low-rank methods on science and engineering.
• 

  FIFA Research Institute

  Silvio Giancola, Research Scientist, Image and Video Understanding Lab

  Oct 6, 12:00 - 13:00

  B9 L2 R2325

  AI Sports FIFA

  This talk will trace the journey from SoccerNet to the creation of the FRI, highlight ongoing projects that bridge cutting-edge research with real-world impact, and discuss what lies ahead at the intersection of AI and sports.
• 

  Silicon-Based mm-Wave Phased-Arrays for 5G/6G and SATCOM

  Abdulrahman Alhamed, Assistant Professor, Electrical and Computer Engineering

  Oct 5, 12:00 - 13:00

  B9, L2, R2325

  The rapid growth of data-intensive applications is creating unprecedented challenges and opportunities in telecommunications. With 5G already leveraging mmWave spectrum and 6G targeting peak data rates approaching 1 Tbps, future networks will demand even broader spectrum allocations across the mmWave and sub-THz bands. Affordable phased arrays have emerged as a cornerstone of this evolution, offering directive communication to overcome severe free-space path loss while enabling narrow beamwidths, high interference tolerance, and adaptive nulling.

Sep 28 - Oct 4, 2025

• 

  AI for Science: AI-Driven Knowledge Discovery

  Dongxiao Zhang, Chair Professor, Faculty of Engineering; Provost and Executive Vice President, Eastern Institute of Technology, Ningbo (EIT)

  Oct 2, 14:30 - 15:30

  B1 L3 R3119

  AI machine learning

  This talk focuses on the latest progress in this area, often called AI for Science, and specifically on how AI is revolutionizing scientific exploration and the uncovering of fundamental physical laws.
• 

  Efficient Bayesian Methods for Biostatistics

  Janet van Niekerk, Research Scientist, Statistics

  Oct 2, 12:00 - 13:00

  B9 L2 R2325

  bayesian methods

  In this talk, I will present some case studies where we approach near real-time inference for complex Biostatistics models, such as disease mapping and brain activation mapping models, among others often encountered in the biostatistics domain, using INLA.
• 

  Towards Finite Element Tensor Calculus

  Kaibo Hu, Associate Professor, Mathematical Institute, University of Oxford

  Sep 30, 14:30 - 15:30

  B1 L3 R3119

  Finite elements tensor calculus PDEs

  In this talk we provide an overview of some efforts to develop finite elements for tensors, motivated by the need for structure-preserving and compatible discretization.
• 

  New Challenges in the Kinetic Theory of Complex Fluids

  Umberto Zerbinati, Stipendiary Lecturer, Oriel College, University of Oxford

  Sep 29, 16:00 - 17:00

  B1 L4 R4214

  PDEs numerical PDEs Kinetic Theory

  This seminar presents a new kinetic theory for complex fluids, detailing the development of a Boltzmann-type equation and discussing its theoretical properties concerning relaxation to equilibrium, hydrodynamic limits, and a novel energy functional for calamitic fluids.
• 

  Robotics at KAUST

  Eric Feron, Professor, Electrical and Computer Engineering

  Sep 29, 12:00 - 13:00

  B9 L2 R2325

  robotics

  Robotics at KAUST is a system integration activity that relies on inputs from Computer Science, Software Engineering, Mechanical Engineering, and Electrical Engineering. A few examples of completed and ongoing robotics research at KAUST will be introduced and discussed. In addition, KAUST's new and large robotics bay will be described in detail.
• 

  Programmable Matter: Liquid Metal for Reconfigurable Electronics and Logic

  Wedyan Babatain, Ibn Rushd Postdoctoral Scholar at Massachusetts Institute of Technology (MIT) Media Lab

  Sep 28, 12:00 - 13:00

  B9 L2 R2325

  liquid metal

  Liquid metal (LM) represents a unique class of programmable matter that combines electrical conductivity with dynamic deformability, enabling the development of reconfigurable electronics and embodied computation. This seminar will discuss electric field-driven control of LM shape and position to achieve tunable, directional LM droplet motion.

Sep 21 - Sep 27, 2025

• 

  Nonparametric Functional Quantiles, Skewness, and Probability Bands via the Functional Signed Directionality

  Emmanuel Ambriz, Postdoctoral Research Fellow, Statistics

  Sep 25, 12:00 - 13:00

  B9 L2 R2325

  functional signed directionality

  We propose the Functional Signed Directionality (FuSD), a nonparametric order for function-valued random elements that defines a pushforward distribution on the real line. This construction enables probabilistic inference in the functional domain: we define set-valued functional quantiles, introduce quantile-based summaries of functional spread and skewness, and construct tight probability bands that reflect the underlying functional law via the FuSD distribution.
• 

  Advice and Comments About Research

  Peter Wonka, Professor, Computer Science

  Sep 22, 12:00 - 13:00

  B9 L2 R2325

  academic life

  This talk provides a collection of advice and commentary on the multifaceted nature of the research process and life as a graduate student.
• 

  Forays into modular drones: Sierpinsky tetrahedra, dodecahedra, and Alexander Graham Bell

  Eric Feron, Professor, Electrical and Computer Engineering

  Sep 21, 12:00 - 13:00

  B9 L2 R2325

  modular drons

  Modular drones offer attractive options for addressing demanding mission requirements without having to build monolithic and large machines. Several such drones have been designed, built, and flown at Georgia Tech's Decision and Control (DCL) laboratory and KAUST's Robotics, Intelligent Systems, and Control (RISC) laboratory. These drones attempt to address some of the perceived weaknesses of prior industrial and academic designs, including lack of structural integrity and possible identity confusion among the modules. Coincidentally, some of the designs echo the fractal kites designed by Alexander Graham Bell more than a century ago and still built and flown today.

Sep 14 - Sep 20, 2025

• 

  Neural Methods for Amortized Inference with Models for Spatial Extremes

  Raphaël Huser, Associate Professor, Statistics

  Sep 18, 12:00 - 13:00

  B9, L2, R2325

  Neural Bayes estimators are neural networks that approximate Bayes estimators. Once trained, these estimators are not only statistically efficient, but also extremely fast to evaluate and amenable to rapid uncertainty quantification. Neural Bayes estimators thus have compelling advantages when used with spatial models that have a computationally intractable likelihood function, as often the case when modeling spatial extremes. In this talk, I will showcase the power of neural Bayes estimators for spatial extremes in a range of climate-related and geo-environmental data applications.
• 

  Geometric Sensor Fusion for Pose Estimation on Riemannian Manifolds

  Mohammed Hussain AlSharif, Postdoctoral Research Fellow, California Institute of Technology (Caltech)

  Sep 18, 11:00 - 12:00

  B1 L3 R3119

  This seminar introduces a novel geometric sensor fusion framework that integrates inertial measurements with acoustic ranging on Riemannian manifolds to achieve robust, high-accuracy pose estimation for autonomous systems in GPS-denied environments.
• 

  From the Ball-Proximal (Broximal) Point Method to Efficient Training of LLMs

  Peter Richtarik, Professor, Computer Science

  Sep 16, 16:00 - 17:00

  B1 L3 R3119

  AI machine learning optimization algorithms LLM

  This talk introduces the Ball-Proximal Point Method, a new foundational algorithm for non-smooth optimization with surprisingly fast convergence, and Gluon, a new theoretical framework that closes the gap between theory and practice for modern LMO-based deep learning optimizers.
• 

  From the Ball-Proximal (Broximal) Point Method to Efficient Training of LLMs

  Peter Richtarik, Professor, Computer Science

  Sep 15, 12:00 - 13:00

  B9 L2 R2325

  AI machine learning optimization algorithms LLM

  This talk introduces the Ball-Proximal Point Method, a new foundational algorithm for non-smooth optimization with surprisingly fast convergence, and Gluon, a new theoretical framework that closes the gap between theory and practice for modern LMO-based deep learning optimizers.
• 

  Optical Frequency Combs: From Conventional Techniques to Emerging Approaches

  Aram Mkrtchyan, Postdoctoral Research Fellow, Electrical and Computer Engineering

  Sep 14, 12:00 - 13:00

  B9 L2 R2325

  Optical frequency combs-optical spectra consisting of many equidistant lines — are powerful tools in modern photonics. The advancements in optical frequency comb generation using high-quality microring resonators (MRRs) have given rise to numerous breakthroughs in metrology, spectroscopy, communications, as well as in quantum computing, quantum data processing, and quantum sources. Under the right conditions, MRRs support dissipative cavity solitons: short optical pulses that circulate in the resonator while maintaining their shape thanks to a balance of dispersion, nonlinearity, gain, and loss.

Sep 7 - Sep 13, 2025

• 

  Gaussian Random Fields on Metric Graphs

  David Bolin, Professor, Statistics

  Sep 11, 12:00 - 13:00

  B9 B2 L2325

  Gaussian random fields Metric graphs Statistical Modeling

  This talk presents a comprehensive mathematical and statistical theory, along with user-friendly software, for modeling data with Gaussian random fields on metric graphs by developing valid covariance functions based on network distance.
• 

  Innovative Multi-Band Antenna Designs for Internet of Sea Applications

  Hanguang Liao, Ph.D. Student, Electrical and Computer Engineering

  Sep 8, 14:00 - 16:00

  B2, L5, R5209

  Monitoring the ocean environment is essential for understanding climate change, protecting marine biodiversity, and enabling sustainable exploitation of marine resources. Human activities such as oil spills and overfishing have significantly disrupted oceanic ecosystems. As a result, there is increasing interest in monitoring marine environments and tracking the health of aquatic species to identify signs of ecological stress. However, acquisition of data from oceans has been a challenging and expensive task. Marine environment lacks adequate communication infrastructures, and traditional solutions such as monitoring ships and underwater cable networks remain prohibitively expensive and logistically complex. These limitations underscore the need for low-cost, scalable, and autonomous ocean monitoring systems.
• 

  Building a Safer and More Equitable Internet in the Age of AI

  Zafar Qazi, Associate Professor, Computer Science, Lahore University of Management Sciences (LUMS)

  Sep 8, 12:00 - 13:00

  B9 L2 R2325

  This talk will show how interdisciplinary collaboration at the intersection of networked systems, AI, and societal impact can help address challenges related to AI-powered moderation systems guiding access to online resources.
• 

  Watching Earth from Space: Methane, Mangroves, and Sinkholes in Saudi Arabia

  Abdulrahman Aljurbua, Assistant Research Professor, KACST; Ibn Rushd Fellow, KAUST; Postdoctoral Scholar Fellowship Trainee in Planetary Science, California Institute of Technology (Caltech)

  Sep 7, 12:00 - 13:00

  B9 L2 R2325

  This talk will present three projects that use satellite remote sensing to address pressing environmental challenges in Saudi Arabia.

Aug 31 - Sep 6, 2025

• 

  From the Ball-Proximal (Broximal) Point Method to Efficient Training of LLMs

  Peter Richtarik, Professor, Computer Science

  Sep 4, 12:00 - 13:00

  B9 L2 R2325

  AI machine learning optimization algorithms LLM

  This talk introduces the Ball-Proximal Point Method, a new foundational algorithm for non-smooth optimization with surprisingly fast convergence, and Gluon, a new theoretical framework that closes the gap between theory and practice for modern LMO-based deep learning optimizers.
• 

  Revolutionizing Datacenter Networks via Reconfigurable Topologies

  Stefan Schmid, Professor, Computer Science, Technische Universität Berlin

  Sep 1, 12:00 - 13:00

  B9 L2 R2325

  This talk presents an overview of reconfigurable datacenter networks. In particular, we discuss the motivation for such reconfigurable architectures, review the technological enablers, and present a taxonomy that classifies the design space into two dimensions: static vs. dynamic and demand-oblivious vs. demand-aware.
• 

  (Ultra)wide Bandgap Semiconductors for Future of Moore’s Law

  Xiaohang Li, Associate Professor, Electrical and Computer Engineering

  Aug 31, 12:00 - 13:00

  B9 L3 R2325

  (Ultra)wide bandgap compound semiconductors including AlN, GaN, Ga2O3 and In2O3 have attracted enormous interests. They offer markedly larger figures of merits for power and RF applications than other known semiconductors. Additionally, they can be applied for vastly impactful quantum information technologies and deep UV-visible optoelectronics. Moreover, they could be promising for More Moore, More than Moore, and Beyond Moore applications. This seminar will cover the latest material, device and IC research based on (ultra)wide bandgap semiconductors for the future of Moore’s Law.

Aug 24 - Aug 30, 2025

• 

  Beyond Connectivity: Paving the Road to Perceptive and Intelligent Networks

  Hesham ElSawy, Associate Professor, School of Computing, Queen’s University

  Aug 26, 13:30 - 14:30

  B1 L3 R3119

  Intelligent Communication connectivity edge computing

  This talk will outline the motivation behind perceptive and intelligent large-scale networks, highlight the technological pillars driving their development, and discuss the key challenges that must be addressed.
• 

  Visual Analytics for Macromolecular Science

  Deng Luo, Ph.D. Student, Computer Science

  Aug 25, 14:00 - 16:00

  B1 L2 R2202; Zoom Meeting 96140008642

  bioinformatics artificial intelligence nanovisualization

  This dissertation presents a suite of scientific visual analytics systems that tightly couple large-scale computational modeling - including both AI-powered inference and traditional molecular simulations - with interactive, scalable visualization.
• 

  Asymptotic Analysis of Precoding in Large-Scale Multi-User Systems

  Xiuxiu Ma, Ph.D., Electrical and Computer Engineering

  Aug 25, 08:30 - 10:00

  B1 L3 R3119

  MIMO Massive MIMO

  This thesis develops and applies novel Gaussian Min-Max Theorems to provide a precise asymptotic performance analysis of complex precoders in massive MIMO systems, successfully characterizing system behavior in previously intractable scenarios involving non-linear post-processing operations.

Jul 27 - Aug 2, 2025

• 

  Toward Robust Multimodal Egocentric Video Understanding

  Merey Ramazanova, Postdoctoral Research Fellow, Computer Science

  Jul 28, 17:00 - 17:45

  B4 L5 R5209; Zoom Meeting 92591807769

  egocentric video Multimodal learning robust modeling

  This thesis advances egocentric video understanding through multimodal learning, large-scale dataset development, and robust adaptation techniques; it introduces new models, benchmarks, and methods for building scalable, resilient perception systems that operate effectively in real-world, first-person environments.

Jul 20 - Jul 26, 2025

• 

  Hardware Centric Quantized Convolutional Neural Network and Algorithms

  Li Zhang, Ph.D. Student, Electrical and Computer Engineering

  Jul 24, 09:00 - 10:00

  B3 L5 R5209

  machine learning accelerators FPGA

  This thesis addresses the challenges of deploying quantized convolutional neural networks (QCNNs) on resource-constrained edge devices by proposing two novel hardware-software co-design frameworks: one for deriving lightweight, hardware-friendly models validated on FPGA, and another for hardware-aware mixed-precision quantization on compute-in-memory accelerators.
• 

  Simulation of Metasurfaces Described by Generalized Sheet Transition Conditions Using Integral Equations

  Sebastian Celis Sierra, Ph.D. Student, Electrical and Computer Engineering

  Jul 23, 10:00 - 11:00

  B3 L5 R5209

  computational electromagnetics Metasurfaces three-dimensional

  This dissertation details the development of several novel integral equation solvers that incorporate Generalized Sheet Transition Conditions (GSTCs) to enable the accurate and computationally efficient simulation of complex, multiscale metasurfaces in three-dimensional problems.

Jul 13 - Jul 19, 2025

• 

  Design of Neuromorphic Object Detection Systems

  Diego Augusto Silva, Ph.D. Student, Electrical and Computer Engineering

  Jul 16, 16:00 - 17:00

  B3 L5 R5209

  event-based object detection neuromorphic vision systems efficient deep learning architectures

  This dissertation advances event-based object detection by developing efficient deep learning frameworks such as ReYOLOv8 and Chimera, introducing novel encoding and augmentation techniques, releasing a new neuromorphic dataset, and demonstrating a real-time, low-power traffic monitoring system that highlights the practical potential of bio-inspired vision systems.
• 

  Randomized Greedy Algorithms for Neural Network Optimization in Solving Partial Differential Equations

  Xiaofeng Xu, Ph.D. Student, Applied Mathematics and Computational Science

  Jul 15, 17:00 - 19:00

  B4 L5 R5220

  PDEs optimization machine learning randomized orthogonal greedy algorithm

  This thesis introduces the randomized orthogonal greedy algorithm (ROGA) to bridge the gap between theoretical and practical performance of shallow neural networks for solving partial differential equations by overcoming key optimization challenges to achieve provably optimal convergence rates.
• 

  Towards Scalable and Efficient Semantic Video Search

  Mattia Soldan, Ph.D. Student, Electrical and Computer Engineering

  Jul 13, 18:00 - 19:00

  B4 L5 R5209

  video-language grounding semantic video retrieval multimodal alignment

  This dissertation advances fine-grained, content-aware video retrieval by developing novel models and frameworks for Video-Language Grounding, enabling accurate alignment between natural language queries and specific temporal segments in unstructured video content.

Jul 6 - Jul 12, 2025

• 

  Discovery of Low-Dimensional Generative Models for Complex Dynamical Systems

  Juan Pablo Muñoz Díaz, Ph.D. Student, Applied Mathematics and Computational Science

  Jul 9, 09:00 - 10:00

  B2 L5 R5220; Zoom Meeting 95274807609

  generative ai applied mathematics bioscience Dynamical Systems deep learning

  This thesis presents a data-driven framework for discovering low-dimensional generative models of complex systems by using a library of normal-form equations to identify both observable dynamics and hidden control variables directly from time-series data.
• 

  Theory and Implementation of Novel Numerical Methods for Multiphysics Interface Problems

  Najwa Alshehri, Ph.D. Student, Applied Mathematics and Computational Science

  Jul 8, 15:00 - 17:00

  B2/B3 L0 R0215

  finite element method numerical analysis fluid-structure interactions mixed finite elements

  This thesis develops and analyzes Finite Element Methods (FEM) for multiphysics interface problems using the Fictitious Domain with Distributed Lagrange Multiplier (FD-DLM) framework. It introduces new families of stable mixed methods with discontinuous Lagrange multiplier spaces, studies both a priori and a posteriori error estimates, and designs multigrid preconditioners. Theoretical results are supported by numerical experiments.
• 

  Towards Usable and Useful Explainable AI

  Lijie Hu, Ph.D. Student, Computer Science

  Jul 7, 17:00 - 19:00

  B3 L5 R5220

  explainable AI Large Language Models multimodal models

  This talk presents advancements in Explainable AI, spanning from classical deep learning to large language models, with contributions that enhance both the usability and usefulness of interpretability methods to improve trust, performance, and safety in AI systems.
• 

  Explainability and Efficiency in Spatio-Temporal Models: Applications to Traffic Forecasting

  Xiaochuan Gou, Ph.D. Student, Computer Science

  Jul 6, 15:00 - 18:00

  B5 L5 R5209

  traffic forecasting Graph Neural Networks model interpretability

  This dissertation addresses key challenges in deep learning-based traffic forecasting, including computational efficiency, model interpretability, and data limitations, despite recent progress in spatio-temporal modeling techniques.
• 

  Modern Privacy-preserving Machine Learning: Rigorous Approach for Data Privacy

  Zihang Xiang, Ph.D. Student, Computer Science

  Jul 6, 10:00 - 12:00

  B3 L5 R5216

  privacy-preserving machine learning Differential privacy Federated learning

  This dissertation centers around privacy-preserving technologies (differential privacy) in broad machine learning applications. This dissertation focuses on two sides of differential privacy: 1) designing privacy-preserving algorithms, 2) ensuring the falsifiability of privacy claims.

Jun 29 - Jul 5, 2025

• 

  Towards Efficient AI Hardware: Software-Hardware Co-Design for In-Memory Computing Accelerators

  Olga Krestinskaya, Ph.D. Student, Electrical and Computer Engineering

  Jun 29, 08:00 - 10:00

  Zoom Meeting 980 9796 2723; B4 L5 R5220

  This dissertation addresses two key challenges in software–hardware co-design for IMC-based neural network accelerators: (1) the need to develop generalized IMC hardware that can efficiently support multiple neural network models, and (2) the need for automated frameworks that jointly optimize model parameters, quantization schemes, and IMC hardware configurations for workload-specific deployments.

Jun 22 - Jun 28, 2025

• 

  Computer Vision for Video Editing Learning to Cut, Classify, Assemble, and Generate

  Alejandro Pardo, Ph.D. Student, Electrical and Computer Engineering

  Jun 23, 10:00 - 12:00

  Click here to join the Ph.D. defense via Zoom

  This thesis advances video editing by developing a suite of computer vision models for understanding and generating editorial decisions, including a method for ranking video cuts, a dataset for classifying cut types, a language-guided timeline assembler, and a diffusion-based technique for creating match cuts.