CS 498

Spring 2026 All Classes

All Classes

Special Topics

SHOW FINAL EXAM SCHEDULE

Credit: 1 TO 4 hours.

Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites.

1 to 4 undergraduate hours. 1 to 4 graduate hours. May be repeated in the same or separate terms if topics vary.

My Favorites

My Schedule

Section Status updates every 10 minutes.

CS 498 class schedule data for spring 2026
CRN	Type	Section	Time	Day	Location	Instructor	Section Details
43751	Lecture-Discussion	AE3	2:00PM -3:15PM	TR	2200 Sidney Lu Mech Engr Bldg	Chekuri, C Harb, E	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Algorithmic Engineering Section Info: Solving Real-World Problems with Theoretical Tools. Description: This course explores the powerful intersection of theory and practice in algorithmic problem-solving, teaching students to apply advanced computational tools like LP solvers, SAT/SMT solvers, metaheuristics, and other modern theoretical tools to real-world engineering, optimization, and decision-making challenges. We explain the theory behind these tools to build intuition, but the emphasis is on application: modeling, using solvers effectively, and engineering robust, efficient solutions. Students will gain hands-on experience working on problems in logistics, verification, scheduling, auctions, online algorithms, and LLMs. By the end of the course, students will not only understand the basic underlying theoretical principles, but more importantly, be equipped to integrate these powerful tools into complex, real-world systems. Prerequisites: CS374 or equivalent coursework with a solid foundation in algorithms. Mathematical maturity. Proficient in programming, with strong experience in Python and/or at least one compiled language such as C, C++, Java, or Rust. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
46303	Lecture-Discussion	AEG	2:00PM -3:15PM	TR	2200 Sidney Lu Mech Engr Bldg	Chekuri, C Harb, E	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Algorithmic Engineering Section Info: Solving Real-World Problems with Theoretical Tools. Description: This course explores the powerful intersection of theory and practice in algorithmic problem-solving, teaching students to apply advanced computational tools like LP solvers, SAT/SMT solvers, metaheuristics, and other modern theoretical tools to real-world engineering, optimization, and decision-making challenges. We explain the theory behind these tools to build intuition, but the emphasis is on application: modeling, using solvers effectively, and engineering robust, efficient solutions. Students will gain hands-on experience working on problems in logistics, verification, scheduling, auctions, online algorithms, and LLMs. By the end of the course, students will not only understand the basic underlying theoretical principles, but more importantly, be equipped to integrate these powerful tools into complex, real-world systems. Prerequisites: CS374 or equivalent coursework with a solid foundation in algorithms. Mathematical maturity. Proficient in programming, with strong experience in Python and/or at least one compiled language such as C, C++, Java, or Rust. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
50445	Lecture-Discussion	AEU	2:00PM -3:15PM	TR	2200 Sidney Lu Mech Engr Bldg	Chekuri, C Harb, E	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Algorithmic Engineering Section Info: Solving Real-World Problems with Theoretical Tools. Description: This course explores the powerful intersection of theory and practice in algorithmic problem-solving, teaching students to apply advanced computational tools like LP solvers, SAT/SMT solvers, metaheuristics, and other modern theoretical tools to real-world engineering, optimization, and decision-making challenges. We explain the theory behind these tools to build intuition, but the emphasis is on application: modeling, using solvers effectively, and engineering robust, efficient solutions. Students will gain hands-on experience working on problems in logistics, verification, scheduling, auctions, online algorithms, and LLMs. By the end of the course, students will not only understand the basic underlying theoretical principles, but more importantly, be equipped to integrate these powerful tools into complex, real-world systems. Prerequisites: CS374 or equivalent coursework with a solid foundation in algorithms. Mathematical maturity. Proficient in programming, with strong experience in Python and/or at least one compiled language such as C, C++, Java, or Rust. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Undergrad - Urbana-Champaign. Not intended for First Time Freshman students.
61928	Online	CC3	ARRANGED	n.a.	n.a.	Farivar, R	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Cloud Computing Applications Section Info: This section is for "on campus" students. This course will be taught on the Coursera platform. Students taking CS courses on the Coursera platform for the first time must take additional steps to correctly setup their Coursera account and complete a brief onboarding course to gain access to the course. Students who enroll in this course must read “Instructions to access CS courses delivered on Coursera platform” available at http://go.cs.illinois.edu/CSregister, failure to follow these instructions will result in late course access. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
59276	Online	CCG	ARRANGED	n.a.	n.a.	Farivar, R	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Cloud Computing Applications Section Info: This course provides a comprehensive overview of modern cloud computing technologies, examining their foundational concepts, economic impact, and transformative potential in enterprise computing. It explores cloud service models, including Infrastructure as a Service, Platform as a Service, and Software as a Service, alongside serverless computing, Big Data programming with Apache Hadoop and Spark, and the role of cloud environments in deploying these systems. The curriculum delves into cloud storage systems, distributed key-value stores, in-memory databases, and advanced data management technologies such as NewSQL, NoSQL, and Spark SQL. Topics also include data analytics, machine learning, graph processing, and real-time data streaming systems like Apache Storm and Spark Streaming. Students gain insights into virtualization, containers, and orchestration tools such as Docker, Kubernetes, and Infrastructure as Code. <br/> This section is for "on campus" students. This course will be taught on the Coursera platform. Students taking CS courses on the Coursera platform for the first time must take additional steps to correctly setup their Coursera account and complete a brief onboarding course to gain access to the course. Students who enroll in this course must read “Instructions to access CS courses delivered on Coursera platform” available at http://go.cs.illinois.edu/CSregister, failure to follow these instructions will result in late course access. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
69511	Online	CCU	ARRANGED	n.a.	n.a.	Farivar, R	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Cloud Computing Applications Section Info: This course provides a comprehensive overview of modern cloud computing technologies, examining their foundational concepts, economic impact, and transformative potential in enterprise computing. It explores cloud service models, including Infrastructure as a Service, Platform as a Service, and Software as a Service, alongside serverless computing, Big Data programming with Apache Hadoop and Spark, and the role of cloud environments in deploying these systems. The curriculum delves into cloud storage systems, distributed key-value stores, in-memory databases, and advanced data management technologies such as NewSQL, NoSQL, and Spark SQL. Topics also include data analytics, machine learning, graph processing, and real-time data streaming systems like Apache Storm and Spark Streaming. Students gain insights into virtualization, containers, and orchestration tools such as Docker, Kubernetes, and Infrastructure as Code. <br/> This section is for "on campus" students. This course will be taught on the Coursera platform. Students taking CS courses on the Coursera platform for the first time must take additional steps to correctly setup their Coursera account and complete a brief onboarding course to gain access to the course. Students who enroll in this course must read “Instructions to access CS courses delivered on Coursera platform” available at http://go.cs.illinois.edu/CSregister, failure to follow these instructions will result in late course access. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Undergrad - Urbana-Champaign.
65868	Online	CDS	ARRANGED	n.a.	n.a.	Farivar, R	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Cloud Computing Applications Section Info: This section is only for students that are in the Computer Science Online MCS/MCS-DS This course provides a comprehensive overview of modern cloud computing technologies, examining their foundational concepts, economic impact, and transformative potential in enterprise computing. It explores cloud service models, including Infrastructure as a Service, Platform as a Service, and Software as a Service, alongside serverless computing, Big Data programming with Apache Hadoop and Spark, and the role of cloud environments in deploying these systems. The curriculum delves into cloud storage systems, distributed key-value stores, in-memory databases, and advanced data management technologies such as NewSQL, NoSQL, and Spark SQL. Topics also include data analytics, machine learning, graph processing, and real-time data streaming systems like Apache Storm and Spark Streaming. Students gain insights into virtualization, containers, and orchestration tools such as Docker, Kubernetes, and Infrastructure as Code. <br/> Program offered on the Coursera platform. Additional ProctorU fees may apply. Restriction(s): Restricted to MCS:Computer Sci Online -UIUC.
61925	Online	DC3	9:00AM -9:50AM	MWF	n.a.	Alawini, A	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Data Management in the Cloud Section Info: Cloud computing has recently seen a lot of attention from research and industry for applications that can be parallelized on shared-nothing architectures and have a need for elastic scalability. As a consequence, new data management requirements have emerged with multiple solutions to address them. This course will look at the principles behind data management in the cloud as well as discuss actual cloud data management systems that are currently in use or being developed. The topics covered in the course range from novel data processing paradigms (MapReduce, Scope, DryadLINQ), to commercial cloud data management platforms (Google BigTable, Microsoft Azure, Amazon S3 and Dynamo, Yahoo PNUTS) and open-source NoSQL databases (Cassandra, MongoDB, Neo4J). The world of cloud data management is currently very diverse and heterogeneous. Therefore, our course will also report on efforts to classify, compare and benchmark the various approaches and systems. Students in this course will gain broad knowledge about the current state of the art in cloud data management and, through a course project, practical experience with a specific system. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
61720	Online	DCG	9:00AM -9:50AM	MWF	n.a.	Alawini, A	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Data Management in the Cloud Section Info: Cloud computing has recently seen a lot of attention from research and industry for applications that can be parallelized on shared-nothing architectures and have a need for elastic scalability. As a consequence, new data management requirements have emerged with multiple solutions to address them. This course will look at the principles behind data management in the cloud as well as discuss actual cloud data management systems that are currently in use or being developed. The topics covered in the course range from novel data processing paradigms (MapReduce, Scope, DryadLINQ), to commercial cloud data management platforms (Google BigTable, Microsoft Azure, Amazon S3 and Dynamo, Yahoo PNUTS) and open-source NoSQL databases (Cassandra, MongoDB, Neo4J). The world of cloud data management is currently very diverse and heterogeneous. Therefore, our course will also report on efforts to classify, compare and benchmark the various approaches and systems. Students in this course will gain broad knowledge about the current state of the art in cloud data management and, through a course project, practical experience with a specific system. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
61721	Online	DCU	9:00AM -9:50AM	MWF	n.a.	Alawini, A	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Data Management in the Cloud Section Info: Cloud computing has recently seen a lot of attention from research and industry for applications that can be parallelized on shared-nothing architectures and have a need for elastic scalability. As a consequence, new data management requirements have emerged with multiple solutions to address them. This course will look at the principles behind data management in the cloud as well as discuss actual cloud data management systems that are currently in use or being developed. The topics covered in the course range from novel data processing paradigms (MapReduce, Scope, DryadLINQ), to commercial cloud data management platforms (Google BigTable, Microsoft Azure, Amazon S3 and Dynamo, Yahoo PNUTS) and open-source NoSQL databases (Cassandra, MongoDB, Neo4J). The world of cloud data management is currently very diverse and heterogeneous. Therefore, our course will also report on efforts to classify, compare and benchmark the various approaches and systems. Students in this course will gain broad knowledge about the current state of the art in cloud data management and, through a course project, practical experience with a specific system. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Undergrad - Urbana-Champaign. Not intended for O/C Engineering City Scholars students.
69525	Discussion/ Recitation Online	DK3 DK3	ARRANGED 11:00AM -12:20PM	n.a. TR	Location Pending n.a.	Kang, D Kang, D	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: AI Agents in the Wild Section Info: This course provides an overview of modern AI agents with a heavy emphasis on implementation. You will learn prompting techniques, agentic loops, modern techniques for splitting work across agents, and other advanced topics. There will be a heavy emphasis on the final project. In lieu of a textbook, this course will require ~$100 of LLM credits. There will be online and in person components. You are responsible for completing homeworks, quizzes, and any in person activities that are required. Prerequisites: CS 447 and one of CS 440, 441, 446. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC.
69526	Discussion/ Recitation Online	DK4 DK4	ARRANGED 11:00AM -12:20PM	n.a. TR	Location Pending n.a.	Kang, D Kang, D	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: AI Agents in the Wild Section Info: This course provides an overview of modern AI agents with a heavy emphasis on implementation. You will learn prompting techniques, agentic loops, modern techniques for splitting work across agents, and other advanced topics. There will be a heavy emphasis on the final project. In lieu of a textbook, this course will require ~$100 of LLM credits. There will be online and in person components. You are responsible for completing homeworks, quizzes, and any in person activities that are required. Prerequisites: CS 447 and one of CS 440, 441, 446. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC.
46398	Discussion/ Recitation Online	DKU DKU	ARRANGED 11:00AM -12:20PM	n.a. TR	Location Pending n.a.	Kang, D	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: AI Agents in the Wild Section Info: This course provides an overview of modern AI agents with a heavy emphasis on implementation. You will learn prompting techniques, agentic loops, modern techniques for splitting work across agents, and other advanced topics. There will be a heavy emphasis on the final project. In lieu of a textbook, this course will require ~$100 of LLM credits. There will be online and in person components. You are responsible for completing homeworks, quizzes, and any in person activities that are required. Prerequisites: CS 447 and one of CS 440, 441, 446. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Undergrad - Urbana-Champaign. Not intended for CS and blended CS majors students.
69512	Discussion/ Recitation Online	DM3 DM3	9:00AM -9:50AM 9:00AM -9:50AM	F MW	Location Pending n.a.	Alawini, A Alawini, A	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Data Management in the Cloud Section Info: Cloud computing has recently seen a lot of attention from research and industry for applications that can be parallelized on shared-nothing architectures and have a need for elastic scalability. As a consequence, new data management requirements have emerged with multiple solutions to address them. This course will look at the principles behind data management in the cloud as well as discuss actual cloud data management systems that are currently in use or being developed. The topics covered in the course range from novel data processing paradigms (MapReduce, Scope, DryadLINQ), to commercial cloud data management platforms (Google BigTable, Microsoft Azure, Amazon S3 and Dynamo, Yahoo PNUTS) and open-source NoSQL databases (Cassandra, MongoDB, Neo4J). The world of cloud data management is currently very diverse and heterogeneous. Therefore, our course will also report on efforts to classify, compare and benchmark the various approaches and systems. Students in this course will gain broad knowledge about the current state of the art in cloud data management and, through a course project, practical experience with a specific system. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Restricted to MCS: Computer Sci OFF - UIUC. Not intended for First Time Freshman students.
69515	Discussion/ Recitation Online	DMG DMG	9:00AM -9:50AM 9:00AM -9:50AM	F MW	Location Pending n.a.	Alawini, A Alawini, A	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Data Management in the Cloud Section Info: Cloud computing has recently seen a lot of attention from research and industry for applications that can be parallelized on shared-nothing architectures and have a need for elastic scalability. As a consequence, new data management requirements have emerged with multiple solutions to address them. This course will look at the principles behind data management in the cloud as well as discuss actual cloud data management systems that are currently in use or being developed. The topics covered in the course range from novel data processing paradigms (MapReduce, Scope, DryadLINQ), to commercial cloud data management platforms (Google BigTable, Microsoft Azure, Amazon S3 and Dynamo, Yahoo PNUTS) and open-source NoSQL databases (Cassandra, MongoDB, Neo4J). The world of cloud data management is currently very diverse and heterogeneous. Therefore, our course will also report on efforts to classify, compare and benchmark the various approaches and systems. Students in this course will gain broad knowledge about the current state of the art in cloud data management and, through a course project, practical experience with a specific system. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Restricted to MCS: Computer Sci OFF - UIUC. Not intended for First Time Freshman students.
61924	Discussion/ Recitation Online	DMU DMU	9:00AM -9:50AM 9:00AM -9:50AM	F MW	Location Pending n.a.	Alawini, A Alawini, A	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Data Management in the Cloud Section Info: Cloud computing has recently seen a lot of attention from research and industry for applications that can be parallelized on shared-nothing architectures and have a need for elastic scalability. As a consequence, new data management requirements have emerged with multiple solutions to address them. This course will look at the principles behind data management in the cloud as well as discuss actual cloud data management systems that are currently in use or being developed. The topics covered in the course range from novel data processing paradigms (MapReduce, Scope, DryadLINQ), to commercial cloud data management platforms (Google BigTable, Microsoft Azure, Amazon S3 and Dynamo, Yahoo PNUTS) and open-source NoSQL databases (Cassandra, MongoDB, Neo4J). The world of cloud data management is currently very diverse and heterogeneous. Therefore, our course will also report on efforts to classify, compare and benchmark the various approaches and systems. Students in this course will gain broad knowledge about the current state of the art in cloud data management and, through a course project, practical experience with a specific system. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Undergrad - Urbana-Champaign. Restricted to O/C Engineering City Scholars students.
67978	Online	DS3	ARRANGED	n.a.	n.a.	Kang, D	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: AI Agents in the Wild Section Info: This section is only for students that are in the Computer Science Online MCS/MCS-DS Program offered on the Coursera platform. Additional ProctorU fees may apply. This course provides an overview of modern AI agents with a heavy emphasis on implementation. You will learn prompting techniques, agentic loops, modern techniques for splitting work across agents, and other advanced topics. There will be a heavy emphasis on the final project. In lieu of a textbook, this course will require ~$100 of LLM credits. Prerequisites: CS 447 and one of CS 440, 441, 446. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Computer Science or Bioinformatics major(s). Restricted to Graduate - Urbana-Champaign. Restricted to MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
67979	Online	DS4	ARRANGED	n.a.	n.a.	Kang, D	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: AI Agents in the Wild Section Info: This section is only for students that are in the Computer Science Online MCS/MCS-DS Program offered on the Coursera platform. Additional ProctorU fees may apply. This course provides an overview of modern AI agents with a heavy emphasis on implementation. You will learn prompting techniques, agentic loops, modern techniques for splitting work across agents, and other advanced topics. There will be a heavy emphasis on the final project. In lieu of a textbook, this course will require ~$100 of LLM credits. Prerequisites: CS 447 and one of CS 440, 441, 446. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Computer Science or Bioinformatics major(s). Restricted to Graduate - Urbana-Champaign. Restricted to MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
61715	Lecture-Discussion	HL3	9:30AM -10:45AM	TR	2039 Campus Instructional Facility	August, T	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Human-LLM interaction Section Info: In this course, we will explore emerging topics in HCI and NLP research to uncover what it means for language technologies to be human centered. We will start with foundational research on human-centered design and this work has been integrated into model development and evaluation. We will learn how ideas in HCI and NLP are intersecting in new and interesting ways, and try our hands at developing some of our own novel language interactions. Classes will be a mix of lectures and seminars, with many class activities planned. The class is research focused, with two implementation focused assignments. We will spend most classes on lectures and in-person discussions around research papers. Students will be expected to read papers, post reading reflections, share and comment on papers and ideas. There will be no exams. Instead, the class will culminate in a research project focused on an emerging topic in HCI+NLP. Classes will not be recorded. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
46400	Lecture-Discussion	HLG	9:30AM -10:45AM	TR	2039 Campus Instructional Facility	August, T	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Human-LLM interaction Section Info: In this course, we will explore emerging topics in HCI and NLP research to uncover what it means for language technologies to be human centered. We will start with foundational research on human-centered design and this work has been integrated into model development and evaluation. We will learn how ideas in HCI and NLP are intersecting in new and interesting ways, and try our hands at developing some of our own novel language interactions. Classes will be a mix of lectures and seminars, with many class activities planned. The class is research focused, with two implementation focused assignments. We will spend most classes on lectures and in-person discussions around research papers. Students will be expected to read papers, post reading reflections, share and comment on papers and ideas. There will be no exams. Instead, the class will culminate in a research project focused on an emerging topic in HCI+NLP. Classes will not be recorded. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
69725	Lecture-Discussion	HLU	9:30AM -10:45AM	TR	2039 Campus Instructional Facility	August, T	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Human-LLM Interaction Section Info: In this course, we will explore emerging topics in HCI and NLP research to uncover what it means for language technologies to be human centered. We will start with foundational research on human-centered design and this work has been integrated into model development and evaluation. We will learn how ideas in HCI and NLP are intersecting in new and interesting ways, and try our hands at developing some of our own novel language interactions. Classes will be a mix of lectures and seminars, with many class activities planned. The class is research focused, with two implementation focused assignments. We will spend most classes on lectures and in-person discussions around research papers. Students will be expected to read papers, post reading reflections, share and comment on papers and ideas. There will be no exams. Instead, the class will culminate in a research project focused on an emerging topic in HCI+NLP. Classes will not be recorded. Restriction(s): Restricted to Undergrad - Urbana-Champaign.
61919	Discussion/ Recitation Online	KC3 KC3	ARRANGED ARRANGED	n.a. n.a.	Location Pending n.a.	Kang, D Kang, D	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: AI Agents in the Wild Section Info: This section is intended for Chicago MCS only. There may be online and in person components. You are responsible for completing homeworks, quizzes, and any in person activities that are required. Please speak with your professor regarding expectations. Weekly in-person meeting in Classroom A at 200 S. Wacker Dr. Chicago. For up-to-date information about CS course restrictions, please see the following link: http:// go.cs.illinois.edu/csregister. Description: This course provides an overview of modern AI agents with a heavy emphasis on implementation. You will learn prompting techniques, agentic loops, modern techniques for splitting work across agents, and other advanced topics. There will be a heavy emphasis on the final project. In lieu of a textbook, this course will require ~$100 of LLM credits. Prerequisites: CS 447 and one of CS 440, 441, 446. Restriction(s): Restricted to Computer Science or Bioinformatics major(s). Restricted to MCS: Computer Sci OFF - UIUC.
61920	Discussion/ Recitation Online	KC4 KC4	ARRANGED ARRANGED	n.a. n.a.	Location Pending n.a.	Kang, D Kang, D	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: AI Agents in the Wild Section Info: This section is intended for Chicago MCS only. There may be online and in person components. You are responsible for completing homeworks, quizzes, and any in person activities that are required. Please speak with your professor regarding expectations. Weekly in-person meeting in Classroom A at 200 S. Wacker Dr. Chicago.For up-to-date information about CS course restrictions, please see the following link: http:// go.cs.illinois.edu/csregister. Description: This course provides an overview of modern AI agents with a heavy emphasis on implementation. You will learn prompting techniques, agentic loops, modern techniques for splitting work across agents, and other advanced topics. There will be a heavy emphasis on the final project. In lieu of a textbook, this course will require ~$100 of LLM credits. Prerequisites: CS 447 and one of CS 440, 441, 446. Restriction(s): Restricted to Computer Science or Bioinformatics major(s). Restricted to MCS: Computer Sci OFF - UIUC.
65904	Lecture-Discussion	LS3	3:30PM -4:45PM	TR	2018 Campus Instructional Facility	Zhang, M	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Machine Learning System Section Info: The goal of this course is to provide students with an in-depth understanding of various elements of modern machine learning systems, ranging from the performance characteristics of ML models such as transformers and diffusers, performance optimization techniques that reduce the compute, memory, and communication for training and inference of large ML models, and compression algorithms that make ML models smaller and cheaper. The course will also conduct case studies on modern large language model training and serving and cover the design rationale behind state-of-the-art machine learning frameworks. Prerequisites: CS 425, CS 446 For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/ CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
60162	Lecture-Discussion	LSG	3:30PM -4:45PM	TR	2018 Campus Instructional Facility	Zhang, M	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Machine Learning System Section Info: The goal of this course is to provide students with an in-depth understanding of various elements of modern machine learning systems, ranging from the performance characteristics of ML models such as transformers and diffusers, performance optimization techniques that reduce the compute, memory, and communication for training and inference of large ML models, and compression algorithms that make ML models smaller and cheaper. The course will also conduct case studies on modern large language model training and serving and cover the design rationale behind state-of-the-art machine learning frameworks. Prerequisites: CS 425, CS 446 For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/ CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
61698	Lecture-Discussion	LSU	3:30PM -4:45PM	TR	2018 Campus Instructional Facility	Zhang, M	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Machine Learning System Section Info: The goal of this course is to provide students with an in-depth understanding of various elements of modern machine learning systems, ranging from the performance characteristics of ML models such as transformers and diffusers, performance optimization techniques that reduce the compute, memory, and communication for training and inference of large ML models, and compression algorithms that make ML models smaller and cheaper. The course will also conduct case studies on modern large language model training and serving and cover the design rationale behind state-of-the-art machine learning frameworks. Prerequisites: CS 425, CS 446 For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/ CSregister Restriction(s): Restricted to Undergrad - Urbana-Champaign.
61930	Lecture-Discussion	NR3	3:30PM -4:45PM	MW	1214 Siebel Center for Comp Sci	Ritschel, N	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Open-Source Software for Educ Section Info: Open-Source Software for Education. Description: This project-based course will teach students about open-source software engineering practices applied to education contexts. Students will learn about how to navigate issues and needs of an open-source projects and how to make contributions to those projects. Students will learn how to engage with stakeholders, how to spec their proposed contributions, and how to document their contributions. Students will work in teams and learn how to create and review pull requests to support higher code quality. Student projects will work closely with faculty from University of Illinois and other institutions to develop software that those instructors can use to support their teaching. Prerequisite: CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC.
61931	Lecture-Discussion	NR4	3:30PM -4:45PM	MW	1214 Siebel Center for Comp Sci	Ritschel, N	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Open-Source Software for Educ Section Info: Open-Source Software for Education. Description: This project-based course will teach students about open-source software engineering practices applied to education contexts. Students will learn about how to navigate issues and needs of an open-source projects and how to make contributions to those projects. Students will learn how to engage with stakeholders, how to spec their proposed contributions, and how to document their contributions. Students will work in teams and learn how to create and review pull requests to support higher code quality. Student projects will work closely with faculty from University of Illinois and other institutions to develop software that those instructors can use to support their teaching. Prerequisite: CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC.
31598	Lecture-Discussion	NRU	3:30PM -4:45PM	MW	1214 Siebel Center for Comp Sci	Ritschel, N	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Open-Source Software for Educ Section Info: Open-Source Software for Education. Description: This project-based course will teach students about open-source software engineering practices applied to education contexts. Students will learn about how to navigate issues and needs of an open-source projects and how to make contributions to those projects. Students will learn how to engage with stakeholders, how to spec their proposed contributions, and how to document their contributions. Students will work in teams and learn how to create and review pull requests to support higher code quality. Student projects will work closely with faculty from University of Illinois and other institutions to develop software that those instructors can use to support their teaching. Prerequisite: CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister Restriction(s): Restricted to Undergrad - Urbana-Champaign.
61923	Lecture-Discussion	QC3	9:30AM -10:45AM	TR	1304 Siebel Center for Comp Sci	Granha Jeronimo, F	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Intro to Quantum Computing Section Info: This course aims to introduce the principles of quantum computing, laying a solid foundation for further advanced courses or research in quantum information. We will tentatively cover the following topics: - Basic concepts and axioms in quantum information, including what a qubit is, what entanglement means, and other related concepts - Fundamental computational operations like quantum gates and measurements - Exchanging quantum information through basic protocols like quantum teleportation and superdense coding - Solving computational problems using quantum algorithms such as Simons' algorithm, Quantum Fourier Transform and phase estimation, Shor's factoring algorithm, Grover search and amplitude amplification - Advanced topics possibly covering quantum complexity, cryptography, error correction, or more This course will take a theoretical computer science perspective on quantum computing. A background in quantum physics is not required, although it can be helpful. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
40484	Lecture-Discussion	QCG	9:30AM -10:45AM	TR	1304 Siebel Center for Comp Sci	Granha Jeronimo, F	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Intro to Quantum Computing Section Info: This course aims to introduce the principles of quantum computing, laying a solid foundation for further advanced courses or research in quantum information. We will tentatively cover the following topics: - Basic concepts and axioms in quantum information, including what a qubit is, what entanglement means, and other related concepts - Fundamental computational operations like quantum gates and measurements - Exchanging quantum information through basic protocols like quantum teleportation and superdense coding - Solving computational problems using quantum algorithms such as Simons' algorithm, Quantum Fourier Transform and phase estimation, Shor's factoring algorithm, Grover search and amplitude amplification - Advanced topics possibly covering quantum complexity, cryptography, error correction, or more This course will take a theoretical computer science perspective on quantum computing. A background in quantum physics is not required, although it can be helpful. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS: Computer Sci OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
47231	Lecture-Discussion	QCU	9:30AM -10:45AM	TR	1304 Siebel Center for Comp Sci	Granha Jeronimo, F	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Intro to Quantum Computing Section Info: This course aims to introduce the principles of quantum computing, laying a solid foundation for further advanced courses or research in quantum information. We will tentatively cover the following topics: - Basic concepts and axioms in quantum information, including what a qubit is, what entanglement means, and other related concepts - Fundamental computational operations like quantum gates and measurements - Exchanging quantum information through basic protocols like quantum teleportation and superdense coding - Solving computational problems using quantum algorithms such as Simons' algorithm, Quantum Fourier Transform and phase estimation, Shor's factoring algorithm, Grover search and amplitude amplification - Advanced topics possibly covering quantum complexity, cryptography, error correction, or more This course will take a theoretical computer science perspective on quantum computing. A background in quantum physics is not required, although it can be helpful. Restriction(s): Restricted to Undergrad - Urbana-Champaign.
78467	Lecture-Discussion	RT3	5:00PM -6:15PM	TR	0216 Siebel Center for Comp Sci	Amato, N Solis Vidana, I	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Robotics Team Project Section Info: This course consists of robotics team projects carried out in simulation and on physical robots, with project tracks such as F1TENTH autonomous driving and RoboCup 2D/3D soccer simulation. Students work in teams to implement and integrate algorithms for perception, localization, motion planning, and control into a complete robotic system that addresses a well-defined robotics challenge drawn from real-world or competition-inspired scenarios. Through hands-on laboratory work and iterative development, students gain strong technical competencies as well as strategic thinking and teamwork skills essential for complex robotics projects. Evaluation is based on demonstrating a fully working robotic system and on a written report and presentation describing the project design, implementation, and results. Prerequisites: Ability to program, CS 124 or CS 101; Data structures (CS 225) is recommended. Calculus 1 and Linear Algebra preferred. Restriction(s): Restricted to Graduate - Urbana-Champaign. Restricted to MCS:Computer Science -UIUC, MS:Computer Science -UIUC, PHD:Computer Science -UIUC, MS:CS:BS/MS Program - UIUC, MCS:BS/MCS Computer Sci -UIUC, or MENG:Engr:AutonomyRobotic-UIUC.
78556	Lecture-Discussion	RT4	5:00PM -6:15PM	TR	Location Pending	Amato, N Solis Vidana, I	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Robotics Team Project Section Info: This course consists of robotics team projects carried out in simulation and on physical robots, with project tracks such as F1TENTH autonomous driving and RoboCup 2D/3D soccer simulation. Students work in teams to implement and integrate algorithms for perception, localization, motion planning, and control into a complete robotic system that addresses a well-defined robotics challenge drawn from real-world or competition-inspired scenarios. Through hands-on laboratory work and iterative development, students gain strong technical competencies as well as strategic thinking and teamwork skills essential for complex robotics projects. Evaluation is based on demonstrating a fully working robotic system and on a written report and presentation describing the project design, implementation, and results. Prerequisites: Ability to program, CS 124 or CS 101; Data structures (CS 225) is recommended. Calculus 1 and Linear Algebra preferred. Restriction(s): Restricted to Graduate - Urbana-Champaign. Restricted to MCS:Computer Science -UIUC, MS:Computer Science -UIUC, PHD:Computer Science -UIUC, MS:CS:BS/MS Program - UIUC, MCS:BS/MCS Computer Sci -UIUC, or MENG:Engr:AutonomyRobotic-UIUC.
78466	Lecture-Discussion	RTU	5:00PM -6:15PM	TR	0216 Siebel Center for Comp Sci	Amato, N Solis Vidana, I	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Robotics Team Project Section Info: This course consists of robotics team projects carried out in simulation and on physical robots, with project tracks such as F1TENTH autonomous driving and RoboCup 2D/3D soccer simulation. Students work in teams to implement and integrate algorithms for perception, localization, motion planning, and control into a complete robotic system that addresses a well-defined robotics challenge drawn from real-world or competition-inspired scenarios. Through hands-on laboratory work and iterative development, students gain strong technical competencies as well as strategic thinking and teamwork skills essential for complex robotics projects. Evaluation is based on demonstrating a fully working robotic system and on a written report and presentation describing the project design, implementation, and results. Prerequisites: Ability to program, CS 124 or CS 101; Data structures (CS 225) is recommended. Calculus 1 and Linear Algebra preferred. Restriction(s): Restricted to Undergrad - Urbana-Champaign. Restricted to CS and blended CS majors or Engineering tuition program students.
61927	Lecture-Discussion	TC3	3:30PM -4:45PM	TR	106B3 Engineering Hall	Erickson, J	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Computational Geometry Section Info: Design and analysis of efficient algorithms for fundamental geometric problems, including convex hulls, Voronoi diagrams, geometric range searching, line segment intersection, polygon triangulation, low-dimensional linear programming, and visibility. Applications of geometric algorithms in computer graphics, mesh generation, geographic information systems, VLSI design, and other areas of computing. A solid background in algorithms (at the level of CS 374) is assumed. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
67785	Lecture-Discussion	TC4	3:30PM -4:45PM	TR	106B3 Engineering Hall	Erickson, J	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Computational Geometry Section Info: Design and analysis of efficient algorithms for fundamental geometric problems, including convex hulls, Voronoi diagrams, geometric range searching, line segment intersection, polygon triangulation, low-dimensional linear programming, and visibility. Applications of geometric algorithms in computer graphics, mesh generation, geographic information systems, VLSI design, and other areas of computing. A solid background in algorithms (at the level of CS 374) is assumed. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
67775	Lecture-Discussion	TCU	3:30PM -4:45PM	TR	106B3 Engineering Hall	Erickson, J	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Computational Geometry Section Info: Design and analysis of efficient algorithms for fundamental geometric problems, including convex hulls, Voronoi diagrams, geometric range searching, line segment intersection, polygon triangulation, low-dimensional linear programming, and visibility. Applications of geometric algorithms in computer graphics, mesh generation, geographic information systems, VLSI design, and other areas of computing. A solid background in algorithms (at the level of CS 374) is assumed. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Undergrad - Urbana-Champaign.
63485	Lecture-Discussion	TZ3	9:30AM -10:45AM	MW	0216 Siebel Center for Comp Sci	Zhang, T	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Intro to Generative AI Section Info: Description: This course introduces modern machine learning techniques for developing and deploying generative models across a range of data modalities. Topics include autoregressive models for text and image generation, such as transformers and GPT-style architectures, with sampling carried out sequentially from conditional distributions. The course also covers image generation approaches including variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, energy-based models, and normalizing flows. Emphasis is placed on model architecture design, training objectives (such as maximum likelihood estimation, adversarial losses, and denoising losses), and inference methods including autoregressive sampling, Langevin dynamics, and Markov chain Monte Carlo (MCMC). Additional topics include multimodal generation, representation learning, foundation model pre-training and post-training, evaluation techniques, safety considerations, and real-world applications. Prerequisite: Students should have prior coursework in machine learning at the level of CS 446 or equivalent, along with a strong background in probability and statistics. Mathematical maturity is expected, including familiarity with advanced linear algebra, multivariable calculus, and abstract probabilistic concepts. Experience with Python programming and numerical libraries such as NumPy and PyTorch is required. Prior exposure to generative models is helpful but not necessary. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC.
63486	Lecture-Discussion	TZ4	9:30AM -10:45AM	MW	0216 Siebel Center for Comp Sci	Zhang, T	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Intro to Generative AI Section Info: Description: This course introduces modern machine learning techniques for developing and deploying generative models across a range of data modalities. Topics include autoregressive models for text and image generation, such as transformers and GPT-style architectures, with sampling carried out sequentially from conditional distributions. The course also covers image generation approaches including variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, energy-based models, and normalizing flows. Emphasis is placed on model architecture design, training objectives (such as maximum likelihood estimation, adversarial losses, and denoising losses), and inference methods including autoregressive sampling, Langevin dynamics, and Markov chain Monte Carlo (MCMC). Additional topics include multimodal generation, representation learning, foundation model pre-training and post-training, evaluation techniques, safety considerations, and real-world applications. Prerequisite: Students should have prior coursework in machine learning at the level of CS 446 or equivalent, along with a strong background in probability and statistics. Mathematical maturity is expected, including familiarity with advanced linear algebra, multivariable calculus, and abstract probabilistic concepts. Experience with Python programming and numerical libraries such as NumPy and PyTorch is required. Prior exposure to generative models is helpful but not necessary. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC.
69364	Lecture-Discussion	TZU	9:30AM -10:45AM	MW	0216 Siebel Center for Comp Sci	Zhang, T	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Intro to Generative AI Section Info: Description: This course introduces modern machine learning techniques for developing and deploying generative models across a range of data modalities. Topics include autoregressive models for text and image generation, such as transformers and GPT-style architectures, with sampling carried out sequentially from conditional distributions. The course also covers image generation approaches including variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, energy-based models, and normalizing flows. Emphasis is placed on model architecture design, training objectives (such as maximum likelihood estimation, adversarial losses, and denoising losses), and inference methods including autoregressive sampling, Langevin dynamics, and Markov chain Monte Carlo (MCMC). Additional topics include multimodal generation, representation learning, foundation model pre-training and post-training, evaluation techniques, safety considerations, and real-world applications. Prerequisite: Students should have prior coursework in machine learning at the level of CS 446 or equivalent, along with a strong background in probability and statistics. Mathematical maturity is expected, including familiarity with advanced linear algebra, multivariable calculus, and abstract probabilistic concepts. Experience with Python programming and numerical libraries such as NumPy and PyTorch is required. Prior exposure to generative models is helpful but not necessary. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Undergrad - Urbana-Champaign.
39547	Discussion/ Recitation Online	ZC3 ZC3	ARRANGED 9:30AM -10:45AM	n.a. MW	Location Pending n.a.	Zhang, T Zhang, T	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 3 hours Section Title: Intro to Generative AI Section Info: This section is intended for Chicago MCS only. In-person exams scheduled in 200 S. Wacker Dr. Description: This course introduces modern machine learning techniques for developing and deploying generative models across a range of data modalities. Topics include autoregressive models for text and image generation, such as transformers and GPT-style architectures, with sampling carried out sequentially from conditional distributions. The course also covers image generation approaches including variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, energy-based models, and normalizing flows. Emphasis is placed on model architecture design, training objectives (such as maximum likelihood estimation, adversarial losses, and denoising losses), and inference methods including autoregressive sampling, Langevin dynamics, and Markov chain Monte Carlo (MCMC). Additional topics include multimodal generation, representation learning, foundation model pre-training and post-training, evaluation techniques, safety considerations, and real-world applications. Prerequisite: Students should have prior coursework in machine learning at the level of CS 446 or equivalent, along with a strong background in probability and statistics. Mathematical maturity is expected, including familiarity with advanced linear algebra, multivariable calculus, and abstract probabilistic concepts. Experience with Python programming and numerical libraries such as NumPy and PyTorch is required. Prior exposure to generative models is helpful but not necessary. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister CS Course Restrictions & Enrollment Caps \| Siebel School of Computing and Data Science \| Illinois CS Course Restrictions & Enrollment Caps Restriction(s): Restricted to Computer Science or Bioinformatics major(s). Restricted to MCS: Computer Sci OFF - UIUC.
46307	Discussion/ Recitation Online	ZC4 ZC4	ARRANGED 9:30AM -10:45AM	n.a. MW	Location Pending n.a.	Zhang, T Zhang, T	Part of Term: 1 Date Range: 01/20/26-05/06/26 Credit: 4 hours Section Title: Intro to Generative AI Section Info: This section is intended for Chicago MCS only. In-person exams scheduled in 200 S. Wacker Dr. Description: This course introduces modern machine learning techniques for developing and deploying generative models across a range of data modalities. Topics include autoregressive models for text and image generation, such as transformers and GPT-style architectures, with sampling carried out sequentially from conditional distributions. The course also covers image generation approaches including variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, energy-based models, and normalizing flows. Emphasis is placed on model architecture design, training objectives (such as maximum likelihood estimation, adversarial losses, and denoising losses), and inference methods including autoregressive sampling, Langevin dynamics, and Markov chain Monte Carlo (MCMC). Additional topics include multimodal generation, representation learning, foundation model pre-training and post-training, evaluation techniques, safety considerations, and real-world applications. Prerequisite: Students should have prior coursework in machine learning at the level of CS 446 or equivalent, along with a strong background in probability and statistics. Mathematical maturity is expected, including familiarity with advanced linear algebra, multivariable calculus, and abstract probabilistic concepts. Experience with Python programming and numerical libraries such as NumPy and PyTorch is required. Prior exposure to generative models is helpful but not necessary. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister CS Course Restrictions & Enrollment Caps \| Siebel School of Computing and Data Science \| Illinois CS Course Restrictions & Enrollment Caps Restriction(s): Restricted to Computer Science or Bioinformatics major(s). Restricted to MCS: Computer Sci OFF - UIUC.