News & Events

Department Events & Announcements

Events

• Apr

  13

  CS Seminar: Reinforcement Learning and Control with Generative World Models (Arindam Banerjee)

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Monday / CS Seminar
  April 13 / 12:00 PM
  Hybrid / Mudd 3514

  Speaker
  Arindam Banerjee, University of Illinois Urbana-Champaign

  Talk Title
  Reinforcement Learning and Control with Generative World Models

  Abstract

  "Recent years have witnessed remarkable advances in generative modeling — from diffusion models and flow matching to autoregressive transformers and action-conditioned video models — that are rapidly closing the gap between learned simulators and the complexity of real-world dynamics. These developments open a principled path toward a new generation of reinforcement learning (RL) algorithms that harness the representational power of generative world models, naturally bridging model-based planning and model-free policy optimization within a unified framework.

  In this talk, we introduce an inference-time policy optimization framework inspired by model predictive control (MPC), built around a pretrained policy and a learned world model (WM) of state transitions and rewards. While existing approaches use learned dynamics to generate imagined trajectories — either during training or at inference — they stop short of using those trajectory rollouts to optimize policy parameters on the fly. Our approach addresses this gap through a Differentiable World Model (DWM) pipeline that enables end-to-end gradient computation through WM trajectory rollouts, yielding inference-time policy optimization (ITPO) grounded in MPC. Across continuous-control benchmarks, ITPO with DWM consistently outperforms strong offline RL baselines. Beyond the core RL framework, we also discuss principled approaches to fine-tuning generative models under distribution shift, which enable the online deployment of such world-model-based policies."

  Biography
  Arindam Banerjee is a Founder Professor at the Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign. He currently serves as the President of the Society for Artificial Intelligence and Statistics which runs the annual international AISTATS conference. He is an ACM Fellow. His research interests are in machine learning and artificial intelligence. His current research focuses on computational and statistical aspects of deep learning, spatial and temporal data analysis, generative models, and sequential decision making. His work also focuses on applications of machine learning in complex real-world and scientific domains including problems in weather and climate, ecology, and agriculture. He has won several awards over the years, including the NSF CAREER award, the IBM Faculty Award, and seven best paper awards at top-tier venues.

  Research Area/Interest:
  Machine Learning, Artificial Intelligence

  ---
  Zoom: TBA
  Panopto: TBA

  more less

  TIME Monday, April 13, 2026 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Mar

  25

  IDEAL:LLMs and Strategic Agents for Machine Learning

  Department of Computer Science (CS)

  1:45 PM Hive 2350, Ford Motor Company Engineering Design Center

  EVENT DETAILS

  Logistics

  Date: Wednesday, March 25th, 2026

  Location: Northwestern University, Ford Motor Company Engineering Design Center (Room: Hive 2350) 2133 Sheridan Rd, Evanston, IL 60201

  Parking: For those driving to the workshop, attendees can park in the North Campus garage 2311 N Campus Dr #2300, Evanston, IL 60208. https://maps.northwestern.edu/txt/facility/646 You’ll exit the garage on the opposite side from the car entrance. It will be a five minute walk to the workshop from the parking garage.

  Registration

  Poster Session Form

  Description:

  This workshop focuses on how strategic agents, potentially including LLM based ones, interact in various machine learning environments and influence the system-wide outcome.

  We are welcoming poster submissions around the following topics (but not restricted to):

  Incentive Issues in LLMs

  Mechanisms for Emerging Technologies such as Generative AIs

  LLM-Based Agents & Coordination

  Multi-agent Reasoning/Debating

  Learning & Adaptation

  Convergence in Strategic Online learning and Bandits

  Preference Learning & Human Feedback

  Information/Text Elicitation from GenAIs

  Fairness / Ethics in LLMs

  Game-Theoretic Foundations

  Robustness & Adversarial Behavior in Strategic Settings

  We are co-locating this workshop with EAI GameNets 2026 – 14th EAI International Conference on Game Theory for Networks GameNets is happening on Mar 26-27 in the same location

  more less

  TIME Wednesday, March 25, 2026 at 1:45 PM - 6:30 PM

  LOCATION Hive 2350, Ford Motor Company Engineering Design Center    map it

  ADD TO CALENDAR

  CONTACT Indira Munoz    indira.munoz@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Apr

  2

  Seminar: Unlocking the Value of Private Data: Differentially Private Synthetic Data Generation (Tianhao Wang)

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Thursday / Seminar
  April 2 / 12:00 PM
  Hybrid / Mudd 3514

  Speaker
  Tianhao Wang, University of Virginia

  Talk Title
  Unlocking the Value of Private Data: Differentially Private Synthetic Data Generation

  Abstract
  Despite massive data generation, access to sensitive datasets for research and development remains severely restricted, leading to "data poverty" and hindering innovation. Differentially private synthetic data generation offers a robust framework to create realistic, privacy-preserving datasets, unlocking their value without compromising individual confidentiality. In this talk, I will highlight our group's recent advancements in this domain, including novel algorithms and comprehensive benchmarking efforts to evaluate the utility and privacy trade-offs of synthetic data and talk about ongoing and future research directions addressing technical challenges and examining approaches across various data modalities.

  Biography
  Tianhao Wang is an Assistant Professor at the Department of Computer Science at University of Virginia (UVA) since Jan 2022. He held a postdoc position at Carnegie Mellon University, earned his Ph.D. in Computer Science from Purdue University in 2021, and B.E. from Fudan University in 2015. His research focus is differential privacy and AI security and privacy. He has extensive publications in top security and database conferences. His work about differentially private synthetic data generation won multiple awards in NIST’s competition.

  more less

  TIME Thursday, April 2, 2026 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Apr

  6

  ME/CS/HCI Seminar- Faez Ahmed

  McCormick - Mechanical Engineering (ME)

  3:00 PM 1-350, Ford Motor Company Engineering Design Center

  EVENT DETAILS

  From Data to Design: Rethinking
  Engineering Design With Next-Gen AI

  BIO

  Faez Ahmed is an Associate Professor of Mechanical Engineering at MIT, where he leads the DeCoDE Lab. His research focuses on AI for engineering design, including deep generative models, multimodal representations, and human–AI collaboration. His work has been recognized with the NSF CAREER Award, ASME DAC and DTM Young Investigator Awards, the Google Research Scholar Award, and the Amazon Research Award. He serves as an Associate Editor for Computer-Aided Design and Design Science.

  ABSTRACT

  Generative AI is transforming how we create, customize, and accelerate digital content. Yet applying these tools to engineering design introduces unique challenges, from maintaining precision under evolving requirements to working effectively in data-scarce environments and interpreting designer intent. In this talk, I will discuss these challenges and show how emerging engineering-focused foundation models are beginning to address them, reshaping workflows in areas such as vehicle design, CAD automation, and design optimization. I will highlight new opportunities enabled by generative AI that integrates multimodal data with engineering analysis and optimization, and present examples of AI-driven design co-pilots for engineering tasks. The talk will conclude with a perspective on how AI enables us to broaden design democratization, accelerate innovation cycles, and fundamentally reshape the role of engineers.

  more less

  TIME Monday, April 6, 2026 at 3:00 PM - 4:00 PM

  LOCATION 1-350, Ford Motor Company Engineering Design Center    map it

  ADD TO CALENDAR

  CONTACT Jeremy Wells    jeremywells@northwestern.edu EMAIL

  CALENDAR McCormick - Mechanical Engineering (ME)

• Apr

  22

  CS Seminar: On the Hardness of Learning Regular Expressions (Lev Reyzin)

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Wednesday / CS Seminar
  April 22 / 12:00 PM
  Hybrid / Mudd 3514

  Speaker
  Lev Reyzin, University of Illinois Chicago

  Talk Title
  On the Hardness of Learning Regular Expressions

  Abstract

  "Despite the theoretical significance and wide practical use of regular expressions, the computational complexity of learning them has been largely unexplored. We study the computational hardness of improperly learning regular expressions in the PAC model and with membership queries. We show that PAC learning is hard even under the uniform distribution on the hypercube, and also prove hardness of distribution-free learning with membership queries. Furthermore, if regular expressions are extended with complement or intersection, we establish hardness of learning with membership queries even under the uniform distribution. We emphasize that these results do not follow from existing hardness results for learning DFAs or NFAs, since the descriptive complexity of regular languages can differ exponentially between DFAs, NFAs, and regular expressions.

  This work is joint with Idan Attias, Nati Srebro, and Gal Vardi"

  Biography
  Lev Reyzin is a Professor of Mathematics, Statistics, and Computer Science at the University of Illinois Chicago and Co-Director of the IDEAL Institute. He works on the theory of machine learning, data science, and artificial intelligence. Prior to UIC, Reyzin was a Simons Postdoctoral Fellow at Georgia Tech and an NSF Computing Innovation Fellow at Yahoo! Research. Reyzin received his Ph.D. on an NSF doctoral fellowship from Yale under Dana Angluin and his bachelor’s degree from Princeton. He is currently the Chair of the Steering Committee for the ALT conference and the Editor-in-Chief of Mathematics of Data, Learning, and Intelligence. He has also served as a General Chair for FOCS 2024, the Program Chair for ISAIM 2020, and a Program Chair for ALT 2017. His work has earned awards at ICML, COLT, and AISTATS and has received extensive funding.

  Research Areas/Interests: theory of machine learning, data science, and artificial intelligence

  ---
  Zoom Link
  Panopto Link

  more less

  TIME Wednesday, April 22, 2026 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Apr

  27

  CS Seminar: Tushar Chandra

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Monday / CS Seminar
  April 27 / 12:00 PM
  Hybrid / Mudd 3514

  Speaker
  Tushar Chandra

  Talk Title
  TBA

  Abstract
  TBA

  Biography
  TBA

  ---
  Zoom: TBA
  Panopto: TBA

  more less

  TIME Monday, April 27, 2026 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Apr

  29

  CS Seminar: Bill Fefferman

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Wednesday / CS Seminar
  April 29 / 12:00 PM
  Hybrid / Mudd 3514

  Speaker
  Bill Fefferman

  Talk Title
  TBA

  Abstract
  TBA

  Biography
  TBA

  ---
  Zoom: TBA
  Panopto: TBA

  more less

  TIME Wednesday, April 29, 2026 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• May

  4

  CS Seminar: Moon Duchin

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Monday / CS Seminar
  May 4 / 12:00 PM
  Hybrid / Mudd 3514

  Speaker
  Moon Duchin

  Talk Title
  TBA

  Abstract
  TBA

  Biography
  TBA

  ---
  Zoom: TBA
  Panopto: TBA

  more less

  TIME Monday, May 4, 2026 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)