Abstract: In high-dimensional data spaces, vast empty regions often exist where no known data points are present. These empty spaces are not merely gaps but hold untapped potential for discovering novel configurations, optimizing parameters, and improving decision-making processes. However, traditional exploration techniques struggle to identify and leverage these regions due to the curse of dimensionality. To address this, we introduce the Empty Space Search Algorithm (ESA), a scalable, physics-inspired method that systematically identifies and explores these uncharted voids. ESA operates by modeling the data space as a dynamic system, using a repulsion-attraction mechanism to locate optimal empty space configurations (ESCs) without requiring exhaustive search. Building upon ESA, we present GapMiner, a visual analytics system that integrates human-in-the-loop AI to iteratively refine and validate ESCs. GapMiner combines parallel coordinate visualization, interactive optimization, and deep learning-based predictive modeling to enhance the efficiency of empty space exploration. This methodology has broad applications, including accelerating convergence in evolutionary algorithms through a more diverse initial population, optimizing adversarial learning strategies, and discovering novel parameter configurations in reinforcement learning. Our approach demonstrates that empty space is not just an absence of data but a frontier for new possibilities in high-dimensional problem-solving.
Bio: Xinyu Zhang received his B.E. in Computer Science from Shandong University, Taishan College, in 2019. He is currently a final-year Ph.D. candidate in the Department of Computer Science at Stony Brook University, advised by Prof. Klaus Mueller. His research focuses on multivariate data analysis, scientific visualization, and reinforcement learning. He has published multiple papers in top-tier journals and conferences, including IEEE TVCG and NeurIPS.
*this seminar will be held in person (food provided on a first come, first serve basis), and online (zoom link below)!
Topic: IACS Student Seminar Speaker: Xinyu Zhang
Time: Feb 26, 2025 12:00 PM Eastern Time (US and Canada)
Join Zoom Meeting
https://stonybrook.zoom.us/j/91848218975?pwd=lfITFa61GaXZ2Wsa1B1OnbLQMmXvOE.1

Meeting ID: 918 4821 8975
Passcode: 027337
CSE 656 Seminars in Computer Vision - Wednesdays 11:30am-12:50pm, Room NCS 120

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 CSE656. 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: Artificial Intelligence for Science (AI4Sci) has become a transformative approach in modeling and understanding complex physical systems, encompassing different scales such as atomistic systems and continuum systems. In atomistic systems, AI has shown potential in accelerating simulations, optimizing molecular dynamics, and predicting material and molecular properties through data-driven approaches, enhancing computational efficiency while preserving accuracy. For continuum systems, AI provides powerful tools for solving partial differential equations (PDEs) and learning physical patterns from data, capturing intricate dynamics that govern physical and engineering processes. This work explores AI methods--particularly equivariance for neural networks and neural operators--bridging atomistic and continuum representations. We analyze the implications of incorporating symmetries to improve model robustness and learning efficiency, providing a cohesive AI- driven framework for advancing scientific discovery. The findings aim to underscore the role of AI in enhancing accuracy, applicability, scalability, interopretability, and generalization across scales, from molecular simulations to physical modeling, opening pathways for next- generation applications in computational science. Biography: Wenhan Gao is a third-year Ph.D. student in Applied Mathematics at Stony Brook University, where he works under the supervision of Professor Yi Liu. Wenhan's research focuses on equivariant neural networks, graph neural networks, and AI for partial differential equations. Wenhan's work seeks to leverage the power of symmetries to aid AI models, particularly in fields such as computer vision (image and video generation), physical simulation (modeling climate change), and computational chemistry (drug discovery). He has published papers on the aforementioned topics in leading venues like NeurIPS, Transactions on Machine Learning Research (TMLR), and Journal of Computational Physics (JCP). He also has several preprints under review in leading venues like ICLR and CVPR. In addition to his research, Wenhan has served as a reviewer for top-tier conferences, including ICLR, NeurIPS, ICML, and KDD, and as a lecturer for undergraduate and graduate courses at Stony Brook University. Wenhan was awarded the NeurIPS Travel Award and Excellence in Teaching for Fall 2023.

Donghee Yvette Wohn, Ph.D.

Inaugural chair of the Department of Technology, AI, and Society, Stony Brook University

Short bio: Dr. Wohn (she/her) is a Professor at the State University of New York at Stony Brook (Stony Brook University), where she is the inaugural chair of the Department of Technology, AI, and Society and director of the Social Interaction Lab (socialinteractionlab.com). Her research is in the area of Human-Computer Interaction (HCI), where she studies the characteristics and consequences of social interactions in online environments. Funded by the National Science Foundation, Mozilla Foundation, and Yahoo, her main projects examine 1) content moderation, online harassment and the creation/maintenance of online safe spaces, 2) social exchange in digital economies & digital patronage (creator-supporter dynamics), and 3) identity and online self-presentation.

Amin Shirangi, PhD candidate in the Department of Technology, AI and Society (DTAS), moderates the discussion.

Location: NCS 120

Zoom: https://stonybrook.zoom.us/j/92841206016?pwd=lj6NYMgwG1OCawgiVGwIalSf1bGWbb.1&jst=2

Abstract: How is AI transforming pricing decisions, and what opportunities, challenges, and risks does this transformation bring? This book traces the evolution of pricing from traditional approaches to today's AI-powered strategies, showing how big data, machine learning, and generative AI are reshaping the way organizations set prices. Pricing decisions can now be adjusted in real time, personalized to individual consumers, and optimized at an unprecedented scale. The book examines the behavioral principles underlying modern pricing, explores how AI enables managers to automate and enhance pricing decisions, and discusses the ethical, legal, and societal challenges raised by these innovations, including concerns about competition, consumer protection, and discrimination. Ultimately, the book argues that AI is not merely changing how prices are set--it is redefining the role of pricing itself, requiring organizations to balance profitability, fairness, and consumer trust.

Speaker Bio: Maxime Cohen is the Scale AI Chair Professor and the Academic Director of the Bensadoun School of Retail Management at McGill University. He is the Chief of AI Strategy of the CIUSSS West-Central Montreal and the Scientific Director of the non-profit MyOpenCourt.org. He was a Visiting Professor of Operations Management and a Shubik Fellow at Yale School of Management. He has collaborated with many companies including Google, Microsoft, Meta, Uber, Waze, Amazon, Expedia, Oracle Retail, IBM Research, Via, Spotify, Aldo Group, Couche- Tard/Circle K, Loblaws, Canadian Tire, L'Oréal, and Staples and he serves on the advisory board of several startups. His research and teaching have received 40+ awards, including Poets&Quants Best 40-Under-40 MBA Professors, RETHINK Retail's Top Retail Influencers, MSOM Young Scholar Prize, and Best OM Paper in Management Science. Finally, he serves on the editorial board of several leading Operations journals (DE at M&SOM and POM, AE at Management Science, OR, and MBR).

Location: Harriman Hall 304


Place:  https://stonybrook.zoom.us/j/99167126152?pwd=TFpEYzM0aFhiOFJxSFJEb1JSS3YyQT09  

Time: 3 PM EST - Dec, 16th, 2020 

Abstract: 

Shadows provide useful cues to analyze visual scenes but also hamper many computer vision algorithms such as image segmentation, object detection, or tracking. For those reasons, shadow detection and shadow removal have been well-studied in computer vision.

Early work on shadow detection and removal focused on physical illumination models of shadows. These methods can express, identify, and remove shadows in a physically plausible manner. However, these models are often hard to optimize and are slow during inference due to their reliance on hand-designed image features. Recently, deep-learning approaches have achieved breakthroughs in performance for both shadow detection and removal. They learn to extract useful features through training while being extremely efficient during inference. However, these models are data-dependent, opaque, and ignore the physical aspects of shadows. Thus they often lack generalization and produce inconsistent results.

We propose incorporating physical illumination constraints of shadows into deep-learning models. These constraints force the networks to more closely follow the physics of shadows, enabling them to systematically and realistically modify shadows in images. For shadow detection, we present a novel Generative Adversarial Network (GAN) based model where the generator learns to generate images with realistic attenuated shadows that can be used to train a shadow detector. For shadow removal, we propose a method that uses deep-networks to estimate the unknown parameters of a shadow image formation model that removes shadows. The system outputs high-quality shadow-free images with little or no image artifacts and achieves state-of-the-art performance in shadow removal when trained on a fully-supervised setting. Moreover, the system is easy to train and constrain since the shadow removal mapping is strictly defined by the simplified illumination model with interpretable parameters. Thus, it can be trained even with a much weaker form of supervision signal. In particular, we show that we can use two sets of patches, shadow and shadow-free, to train our shadow decomposition framework via an adversarial system. These patches are cropped from the shadow images themselves.
Therefore, this is the first deep-learning method for shadow removal that can be trained without any shadow-free images, providing an alternative solution to the paired data dependency issue. The advantage of this training scheme is even more pronounced when tested on a novel domain such as video shadow removal where the method can be fine-tuned on a testing video with only the shadow masks generated by a pre-trained shadow detector and further improves shadow removal results.

AI use statements help students understand whether, when, and how AI fits into their coursework.

Explore how to connect those expectations to your learning goals and communicate them clearly at both the course and assignment levels.

In this session, learn how to:

  • Draft or revise a course-wide AI use statement for your syllabus.
  • Develop assignment-specific guidance aligned with learning goals.
  • Communicate AI expectations that reflect your instructional goals.

Register to attend.
Join Stony Brook University's Center for Excellence in Learning and Teaching (CELT) for a bootcamp on how to use AI to enhance your teaching and courses. This event will demonstrate how ChatGPT, Microsoft Copilot, and other generative AI platforms can support you in crafting learning objectives, writing exam questions, composing rubrics, and designing course content such as lesson plans, in-class activities, instructional videos, and more.

Register here.