Inside Our ProgramProgram Events
Events
-
Nov13
EVENT DETAILSmore info
lessReinforcement learning has become a standard tool for post-training language models and teaching them to reason, follow instructions, and align with human preferences. Nevertheless, the ingredients that produce this reasoning capability are still only partly understood: reward models, the construction of verifiers, and long chains of thought optimized end to end against sparse reward signals.
This workshop investigates formal characterizations of reasoning and the role of reinforcement learning in promoting reasoning capability. Does post-training introduce new capabilities, or does it sharpen a distribution the base model already contains? How should credit be assigned across tokens when the only feedback is whether the final answer was correct? What happens when the verifier is imperfect, the reward is subject to hacking, or the task admits answers that are difficult to verify? Potential topics include:
RL from human feedback, preference optimization, and reward modeling
RL with verifiable rewards; automated verification for mathematics, code, and formal reasoning
Credit assignment and exploration over long reasoning traces
Theoretical accounts of post-training (e.g., sample complexity and generalization)
Reward hacking, specification gaming, and the robustness of learned verifiers
Multi-turn, agentic, and tool-using settings; RL for language-model agents
Evaluation of reasoning; data and benchmarks for reasoningThe one-day event consists of invited talks and a poster session, and aims to foster connections among researchers in reinforcement learning, natural language processing, learning theory, optimization, statistics, and related areas.
TIME Friday, November 13, 2026 at 9:15 AM - 5:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Bella Barrios marbella.barrios@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Nov14
EVENT DETAILSmore info
lessWant to join the decision-makers? Register for Northwestern University's Master of Science in Information Technology (MSIT) Program Information Session and learn how you can enhance your knowledge of IT and gain the business management skills you need to direct effective IT strategy.
TIME Saturday, November 14, 2026 at 11:00 AM - 1:30 PM
LOCATION McCormick Education Center STE 1400
CONTACT Svetlana Korzeniowski msit@northwestern.edu EMAIL
CALENDAR MS in Information Technology (MSIT) Program
-
Nov16
EVENT DETAILS
lessMonday / CS Seminar
November 16 / 12:00 PM
Hybrid / Mudd 3514Speaker
Zain Saleem, Argonne National LaboratoryTalk Title
Modular Quantum ComputingAbstract
Connecting smaller quantum processors offers a path toward scalable quantum computing, but requires efficient ways to divide computations, communicate between modules, and protect against errors. In this talk, I will discuss our work on these challenges, beginning with circuit cutting, which reconstructs larger computations from smaller experiments, and its applications to optimization and error mitigation. I will then explain how the sampling cost of circuit cutting motivates quantum links and examine the conditions under which these links can offer an advantage. Finally, I will present approaches to distributed quantum error correction that concentrate protection at noisy interfaces and limit the spread of connection faults. These examples highlight how algorithms, quantum communication, and error correction can be designed together to make small quantum processors work as a larger system.Biography
Zain H. Saleem is a Scientist in the Mathematics and Computer Science Division at Argonne National Laboratory. His research focuses on distributed quantum computing, quantum algorithms, and quantum error correction, with broader interests in quantum sensing and entanglement dynamics. He holds a master’s degree from the University of Cambridge and a Ph.D. in physics from the University of Pennsylvania, where his doctoral research focused on black hole physics. Before joining Argonne, he worked as a quantitative associate at Morgan Stanley.TIME Monday, November 16, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Nov17
EVENT DETAILS
lessTuesday / CS Seminar
November 17 / 12:00 PM
Hybrid / Mudd 3514Speaker
Nathan Nichols,Tableau/SalesforceTalk Title
AI Safety from the Inside: Notes from 20 Years of Building AIAbstract
Nate Nichols has spent two decades building and shipping AI products, from machine-generated content research during his CS PhD, to Chief Scientist at an NLG startup, to VP of Product at Salesforce. Lately he’s been asking a different question: what happens as these systems get more capable than the people building them expect? In this informal talk, he’ll share how his thinking on AI safety has changed, what the field’s open problems look like from a practitioner’s seat, and why people entering AI right now are unusually well placed to shape how it goes. Bring questions.Biography
As VP of Product Management at Tableau/Salesforce, Nate owns the Agentic Analytics strategy and works with product development teams across Tableau to define and communicate that vision. Nate was previously Chief Scientist at Narrative Science (acquired by Tableau in 2021) and has over 40 patents related to text generation and rhetorical modeling. He earned his Ph.D. in Artificial Intelligence from Northwestern University in 2010, with a thesis titled “Machine-generated Content.” Since 2025, Nate has become passionate about AI safety, leading public workshops in Chicago and hosting Kitchen Table, a weekly podcast and YouTube show dedicated to engaging parents and the public on AI safety topics.Research Interest/Area: AI safety
TIME Tuesday, November 17, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Nov18
EVENT DETAILS
less
Please join us in the Electrical and Computer Engineering Department at the Technological Institute for a Meet-the-Faculty Seminar with Professor Brenna Argall, PhD, from Northwestern University.
There will be a brief reception post-seminar.
Abstract: As need increases, access decreases. It is a paradox that as human motor impairments become more severe, and increasing needs pair with decreasing motor ability, the very machines created to provide assistance become less and less accessible to operate with independence. My lab addresses this paradox by incorporating robotics autonomy and intelligence into machines that enable mobility and manipulation: leveraging robotics autonomy, to advance human autonomy. In this talk, I will discuss distinct challenges and opportunities within this domain, and overview a sampling of projects and studies within my lab.
Bio: Brenna Argall is a professor of Mechanical Engineering, Computer Science, and Physical Medicine & Rehabilitation at Northwestern University. She is founder and director of the assistive & rehabilitation robotics laboratory (argallab) at the Shirley Ryan AbilityLab (formerly Rehabilitation Institute of Chicago), the #1-ranked rehabilitation hospital in the United States. The mission of the argallab is to advance human ability by leveraging robotics autonomy. Argall is a Fellow of the American Institute for Medical and Biological Engineering (2023), a recipient of the NSF CAREER award (2016), and one of the 40 under 40 by Crain’s Chicago Business (2016). Her Ph.D. in Robotics (2009) was received from the Robotics Institute at Carnegie Mellon University, as well as her B.S. in Mathematics (2002). She has been a research fellow at the National Institutes of Health (2002-2004), the École Polytechnique Fédérale de Lausanne (EPFL, 2009-2011), and the Wyss Center for Bio and Neuroengineering (2019) in Geneva, Switzerland.
TIME Wednesday, November 18, 2026 at 2:45 PM - 4:30 PM
LOCATION L440, Technological Institute map it
CONTACT Lee Onysko lee.onysko@northwestern.edu EMAIL
CALENDAR Department of Electrical and Computer Engineering (ECE)
-
Nov19
EVENT DETAILS
lesstba
TIME Thursday, November 19, 2026 at 9:00 AM - 11:00 AM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Dec4
EVENT DETAILS
lessTBA
TIME Friday, December 4, 2026 at 12:00 PM - 2:00 PM
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Dec9
EVENT DETAILS
lessInformation systems have become the cornerstone of how decisions are made in nearly every domain of human activity, constituting the infrastructure through which knowledge is accessed and acted upon. At their core, an information system is any integrated combination of hardware, software, databases, networks, and human expertise organized to collect, process, store, and analyze information in support of operations and decision-making. The usability of such systems in practice is governed by two properties that have historically stood in tension: accuracy and fluency. Symbolic, query-based systems offer high accuracy but require specialized query languages or code to interact with effectively, while large language model (LLM)-based systems are fluent and accessible through natural language but remain prone to hallucination and factual error. The goal of this dissertation is twofold: to build information systems that answer questions and generate reports from data both accurately and fluently, and to generate training data that improves the accuracy and fluency of such systems, in both cases by using structured knowledge and rules as a source of ground truth for language generation.
To this end, this dissertation introduces a neurosymbolic framework, grounded in knowledge representations of data and analytics, that first produces language outputs that are accurate but not necessarily fluent, and then uses these outputs to condition LLM generation, yielding final outputs that are both accurate and fluent. These outputs can serve two roles: as the final product delivered to a user, or as training data for the models that later serve users. This framework is first demonstrated through Satyrn, a report generation system in which domain-independent report blueprints produce accurate but coarse information that is then used to condition LLMs, jointly producing reports that are more factual, fluent, and coherent than those generated by existing neural methods. The framework is then applied to training data generation through RingSQL, a platform that combines these knowledge representations with LLM-based paraphrasing to produce text-to-SQL training data that is as diverse and fluent as LLM-generated data while remaining more accurate and faithful to the underlying query. Data generated with RingSQL provides a stronger training signal than data produced with prior LLM-based methods, template-based methods, and even human-annotated data. Finally, this dissertation introduces methods for grounding the generation of reasoning traces in verifiable, rule-based evaluation, and uses these traces in a mixed-policy reinforcement learning setting, offering an additional path toward improving the accuracy of LLM-based information systems. Together, these contributions demonstrate that structured knowledge and language are complementary, and that unifying them can reconcile the accuracy-fluency trade-off in information systems.TIME Wednesday, December 9, 2026 at 6:00 PM - 8:00 PM
CONTACT Jensen Smith jensen.smith@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
