Computer Science and Engineering | Michigan State University | Where computer science meets the world

High Ranking

Computer Science Doctoral Program Highly Ranked

Research@CSE

Laboratories and research groups with a diverse range of interests are why MSU CSE is where computer science meets the world. We invite you to explore how we meet the challenges of developing technology to benefit society and advance scientific knowledge

Degree Programs

Each year the department awards degrees in Computer Science for the BS, MS, and PhD. In addition, the Department administers an undergraduate Computer Engineering degree program jointly with the Department of Electrical and Computer Engineering.

Events

CSE Lecture Series

Bio: Chuxu Zhang is an Associate Professor of Computer Science and Engineering at the

University of Connecticut, specializing in the intersection of graph machine learning, large

language models, and their societal applications in areas like public health, healthcare, social

media, and cybersecurity. His recent work focuses on developing foundational, resourceefficient, and safe AI models and algorithms for graph and language data. His work is mainly

published in top machine learning and data science conferences, including ICML, NeurIPS,

ICLR, KDD, WWW, NAACL, and EMNLP. He has earned several prestigious honors, including

the NSF CAREER Award (2024), the Frontiers of Science Award (2024), the AAAI New Faculty

Highlight (2023), and Best Paper (Candidate) Awards at CIKM 2021, WWW 2019, and WAIM

2016. He serves as an associate editor for Transactions on Machine Learning Research and

ACM Transactions on Intelligent Systems and Technology.

Abstract: The rapid advancement of AI has inspired us to harness its capabilities to tackle

some complex challenges facing society today. In this talk, I will share insights from our recent

research, with a focus on developing AI models (in particular, graph neural networks and

language models) that are not only foundational but also resource-efficient and safe. I will

discuss how these advanced techniques can be applied to solve critical societal issues across

multiple domains, including public health, healthcare, social media, and cybersecurity.

Host: Prof. Jiliang Tang tangjili@msu.edu - Department of Computer Science and Engineerin

Bio: Justin Hsia is an Associate Teaching Professor at the Paul G. Allen School of Computer

Science & Engineering at the University of Washington. He primarily teaches computer

engineering courses and also focuses on the training and mentoring of teaching assistants and

instructors, including originating the role of CSE Summer Courses Coordinator and co-chairing

the Teaching Faculty Recruiting Committee. He has received the UW ACM Teaching Award

and has been nominated for the UW Distinguished Teaching Award. He received his Ph.D. in

Electrical Engineering and Computer Sciences from the University of California, Berkeley.

Abstract: Computer science (CS) post-secondary programs continue to proliferate

and expand in response to the still-unmet student demand for computational skills.

To meet this demand, institutions are increasingly creating and hiring for teachingfocused positions (i.e., positions where at least 50% of time is spent on teaching).

However, hiring efforts are stymied, in part, by mismatches between the expectations

of hiring committees and available opportunities designed to prepare new instructors

for post-secondary teaching positions, leading to a lack of qualified candidates.

In this talk, I will discuss how we can better prepare students for post-secondary CS

teaching careers, including ideas for increasing teaching career visibility, teachingrelated opportunities, and access to teaching careers. Throughout, I will include

current and planned efforts in the Paul G. Allen School of Computer Science &

Engineering (CSE) at the University of Washington toward making post-secondary

CS teaching a visible, “first-class” career option for its undergraduate and graduate

students, alongside the more common industry and research pathways, as well as

insights and alternate efforts from other institutions.

Host: Prof. Laura Dillon

Bio: Pan Li has joined Georgia Tech. ECE department as an assistant professor since 2023, and has

previously worked as an assistant professor at Purdue CS since 2020. Pan's research interest lies

broadly in the area of machine learning and optimization with graph data. Pan Li's work has been

recognized by several awards including NSF Early Career Award, several industry research awards from

Meta, JPMorgan, Sony, Amazon, the Best Paper award at the Learning on Graph Conference 2022 and

the Best Paper award nomination at the Web Conference 2021.

Abstract: The application of Graph Machine Learning (GML) and Geometric Deep Learning (GDL) to

enhance prediction capabilities for graph-structured data and point cloud data is prevalent in scientific

disciplines. However, these applications often present fundamental challenges in model computation

and generalization due to the ultra-large data scale and unstable data distribution. Specifically,

applications in particle physics require processing point clouds on the scale of 10,000 points with a

latency requirement of O(ms). Moreover, in scientific research, the data used for model training often

comes from thoroughly investigated regimes, whose distributions frequently do not align well with the

under-explored regimes, though only the latter attract research interest. Additionally, the mutual

dependence of entities in a graph or point cloud breaks the assumptions adopted by most previous

works, necessitating new problem formulations and principled methodologies. In this talk, I will

introduce our recent studies addressing these problems and show their applications in network data

and particle flow data in high-energy physics. Some relevant papers are:

1. Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy

Physics, Miao et al., ICML 2024 (selected for oral presentation)

2. Structural Re-weighting Improves Graph Domain Adaptation, Liu et al., ICML 2023

3. Pairwise Alignment Improves Graph Domain Adaptation, Liu et al., ICML 2024 (selected for spotlight

presentation)

Host: Prof. Jiliang Tang tangjili@msu.edu,Department of Computer Science and Engineering

Planning Agents for Collaborative Reasoning and Multimodal Generation

Abstract: In this talk, I will present our journey of developing diverse, adaptive, uncertainty-calibrated AI planning agents that can robustly communicate and collaborate for multi-agent reasoning (on math, commonsense, coding, etc.) as well as for interpretable, controllable multimodal generation (across text, images, videos, audio, layouts, etc.). In the first part, we will discuss improving reasoning via multi-agent discussion among diverse LLMs and its structured distillation to smaller, open-source models (ReConcile, MAGDi), as well as making LLMs better teammates through confidence calibration (using speaker-listener pragmatic reasoning) and by teaching them to accept/reject persuasion as appropriate. In the second part, we will discuss interpretable and controllable multimodal generation via LLM-agents based planning and programming, such as layout-controllable image generation (and evaluation) via visual programming (VPGen+VPEval), consistent multi-scene video generation via LLM-guided planning (VideoDirectorGPT), interactive and composable any-to-any multimodal generation (CoDi, CoDi-2), as well as multi-agent interaction for adaptive environment/data generation based on discovered weak skills (EnvGen, DataEnvGym).

Bio: Dr. Mohit Bansal is the John R. & Louise S. Parker Distinguished Professor and the Director of the MURGe-Lab (UNC-NLP Group) in the Computer Science department at UNC Chapel Hill. He received his PhD from UC Berkeley in 2013 and his BTech from IIT Kanpur in 2008. His research expertise is in natural language processing and multimodal machine learning, with a particular focus on multimodal generative models, grounded and embodied semantics, reasoning and planning agents, faithful language generation, and interpretable, efficient, and generalizable deep learning. He is a AAAI Fellow and recipient of the Presidential Early Career Award for Scientists and Engineers (PECASE), IIT Kanpur Young Alumnus Award, DARPA Director's Fellowship, NSF CAREER Award, Google Focused Research Award, Microsoft Investigator Fellowship, Army Young Investigator Award (YIP), DARPA Young Faculty Award (YFA), and outstanding paper awards at ACL, CVPR, EACL, COLING, CoNLL, and TMLR. He has been a keynote speaker for the AACL 2023, CoNLL 2023, and INLG 2022 conferences. His service includes EMNLP and CoNLL Program Co-Chair, and ACL Executive Committee, ACM Doctoral Dissertation Award Committee, ACL Americas Sponsorship Co-Chair, and Associate/Action Editor for TACL, CL, IEEE/ACM TASLP, and CSL journals. Webpage: https://www.cs.unc.edu/~mbansal/