The overall purpose of this seminar is to bring together people with interests in Computer Vision theory and techniques and to examine current research issues. This course will be appropriate for people who already took a Computer Vision graduate course or already had research experience in Computer Vision. To enroll in this course, you must either: (1) be in the PhD program or (2) receive permission from the instructors.

Each seminar will consist of multiple short talks (around 10 minutes) by multiple people. Students can register for 1 credit for CSE 656. Registered students must attend and present a minimum of 2 or 3 talks. Everyone else is welcome to attend. Fill in https://forms.gle/pCVXovgfMfQwGqG38 to subscribe to our mailing list for further announcement.

Abstract: Implicit functions have long been a fundamental representation for both 2D and 3D objects in computer graphics, playing a significant role in the field's early development. With the rise of 3D deep learning and the rapid advancement of neural rendering techniques, implicit representations of 3D shapes have regained significant attention in recent years. In this talk, I will present several recent research projects focusing on implicit function-based 3D reconstruction and neural rendering. Furthermore, I will discuss potential future developments in this dynamic and rapidly evolving field.

Biography: Ying He is an Associate Professor at the College of Computing and Data Science, Nanyang Technological University, where he also serves as the Director of the Centre for Augmented and Virtual Reality. His research interests lie in geometric computation and analysis, with applications spanning computer graphics, 3D vision, computer-aided design, multimedia, and wireless sensor networks. Dr. He is an active member of the technical program committees for major conferences on geometric modeling and has served on the editorial boards of IEEE Transactions on Visualization and Computer Graphics, Computer Graphics Forum, and Computational Visual Media. He has also taken on key leadership roles as General/Program Co-Chair for several conferences, including Shape Modeling International (SMI) 2022, Solid and Physical Modeling (SPM) 2022 & 2023, Geometric Modeling and Processing (GMP) 2014 & 2021, and Computational Visual Media (CVM) 2020. For more information, please visit https://personal.ntu.edu.sg/yhe/

Location: NCS 115

CG Group member (and SBU faculty) Chao Chen will speak on Fri, March 12, about the use of topological data analysis in machine learning for image analysis.
Chao has shared some of his research with the CG Group previously, and this will be a great opportunity to learn more about this exciting research area related to computational geometry/topology!

Time: Friday, March 12, 2pm-3pm
Place: Zoom
https://stonybrook.zoom.us/my/profweizhu?pwd=RjVIVXg3YUhudzZZQ3pheHUydTJBUT09



Title: Learning with Topological Information - Image Analysis and Label Noise
Speaker: Prof. Chao Chen (SBU)

Abstract: Modern machine learning faces new challenges. We are
analyzing highly complex data with unknown noise. Topology provides
novel structural information to model such data and noise. In this
talk, we discuss two directions in which we are using topological
information in the learning context. In image analysis, we propose a
topological loss to segment and to generate images with not only
per-pixel accuracy, but also topological accuracy. This is necessary
in analysis of images of fine-scale biomedical structures such as
neurons, vessels, etc.  Extracting these structures with correct
topology is essential for the success of downstream
analysis. Meanwhile, we discuss how to use topological information to
train classifiers robust to label noise. This is important in practice
especially when we are using deep neural networks which tend to
overfit noise. These results have been published in NeurIPS, ECCV,
ICML and ICLR.

AI is everywhere -- and so are the privacy concerns that come with it. At its core, the most common forms of AI we use today are online digital services -- and thus inherit the usual privacy risks of any internet-based tool. However, AI also introduces a set of unique and evolving risks. We'll take a closer look at one of the newest developments in this area: indirect prompt injection -- a technique that can trick AI tools into revealing or extracting private information. You'll learn how this emerging form of AI manipulation works, why it matters, and how to protect yourself -- as well as how similar techniques are being used in academic contexts to manipulate systems and even mislead researchers.

Register for this Zoom workshop.

I will be holding an informal 2-week short optimization course, to try
to cover a few important proofs in the field. The goal will be depth
over breadth, with focus on:

 - convergence proofs for gradient descent and stochastic gradient descent
 - energy functions and continuous time optimization
 - estimate sequences and Nesterov acceleration

and, time permitting, additional topics like variance reduction,
quasi-Newton methods, and Frank-Wolfe methods. If we go super fast, we
can spend a few days at the end brainstorming interesting research
project ideas.

Details: NCS 220 6:15pm-7:45pm, Monday-Friday, Feb 7-Feb 18.

In person only, since I plan to use the whiteboard (but may be recorded)

More details will be uploaded here (notes, specific schedule):
https://sites.google.com/view/optimization-short-course/home
TITLE: Towards a Theory of Encode/Decoder Architectures by Andrej Risteski of CMU

ABSTRACT: A common choice of architecture in representation learning (i.e., learning a good embedding of the data) is an encoder/decoder architecture, which tries to map a part of the input into a good latent representation (via an encoder), and predict the remaining part of the input (via a decoder). Two common examples are universal machine translation: where one tries to learn to translate between any pair of a set of languages via a common latent language, given paired up corpora for only a part of the pairs; and contextual encoders -- where one tries to predict a part of the image, given the rest of the image.
 
We will give a framework for analyzing the sample complexity of such architectures -- i.e., how many pairs of languages do we need to have paired up corpora for? How many image prediction tasks do we have to solve to get a good representation?


New York Scientific Data Summit (NYSDS) is a premier annual conference that brings together researchers and thought leaders from academia, national labs and industry to exchange ideas and foster collaboration focused on data-driven science and technology. Co-hosted by Brookhaven National Laboratory and the Institute for Advanced Computational Science (IACS) at Stony Brook University, NYSDS 2025 will take place on September 11-12, 2025, in the SUNY Global Center in New York City.

NYSDS 2025 will spotlight artificial intelligence (AI), machine learning (ML) and robotics - fields currently at a pivotal point with transformative impacts on science and technology. From accelerating computationally demanding simulations to discerning signals from noisy data, AI/ML has become an integral part of the scientific workflows. Despite many advances, challenges remain to ensure that AI/ML applications are reliable, explainable and trustworthy.

Robotics, a growing field that couples AI with physically actuated mechanical bodies, has seen increased interest in areas spanning science, technology and manufacturing. The need for real-time decision-making and control, along with the intricate morphology of robots, makes robotics an intriguing application of AI, advanced computing and optimization.


This NYSDS 2025 is open to the public. To be eligible to attend, all participants must register online by August 30, 2025. For questions or assistance with registering, please contact the Summit Coordinator.

Register here.