CS622 Advanced Methods in Artificial Intelligence
CS622 Advanced Methods in Artificial Intelligence
Syllabus | International University of Sarajevo - Last Update on Oct 10, 2026
Syllabus Quick Jump
Search and navigate to any syllabus instantly
Computer Sciences and Engineering
Ali Almisreb
Course Lecturer
Course Objectives
This doctoral course builds on CS511 Advanced Artificial Intelligence (large language models, vision-language models and agents) and moves to the research frontier: the theory behind why foundation models work, alternative architectures and generative paradigms, interpretability and alignment, reasoning and world models, and the science of evaluation. Each week combines a technical lecture (derivations and the key results of recent papers) with critical reading of primary literature. Students write peer reviews, reproduce a recent paper, and carry out an original research project aimed at a workshop or conference submission. Learning outcomes. On successful completion, students will be able to:
- Analyse the theoretical foundations of foundation models: expressivity, in-context learning, optimization and scaling, and the mathematics of diffusion/flow and state-space models.
- Apply and critically assess frontier methods in interpretability, alignment, reasoning, world models and multimodal learning, including their assumptions and failure modes.
- Critically review recent research papers at the standard of a programme committee member and identify open problems.
- Reproduce a published result and design rigorous experiments with sound statistical analysis and compute-aware ablations.
- Formulate, execute and communicate an original research contribution as a paper suitable for submission to a peer-reviewed venue.
Learning Outcomes
After successful completion of the course, the student will be able to:
Course Materials
Required Textbook
Additional Literature
Teaching Methods
The course is run as a research seminar
Each week the instructor presents the technical background and derivations; students read the assigned primary papers in advance, submit a structured review of one paper in conference format (summary, strengths, weaknesses, questions, score), and one student leads the discussion
Students reproduce the main result of a recent paper and conduct an original research project, individually or in pairs, with the goal of a workshop or conference submission
Research progress is discussed in individual meetings with the instructor
Weekly Topics
| Week | Topic | Readings / References |
|---|---|---|
| 1 | Research Methodology for Frontier AI | Lipton & Steinhardt (2019) Troubling trends in ML scholarship; Dodge et al. (2019) Show your work |
| 2 | Theory of Transformers and In-Context Learning | Garg et al. (2022); von Oswald et al. (2023); Olsson et al. (2022); Merrill & Sabharwal (2024); Schaeffer et al. (2023) |
| 3 📍 | Optimization and the Science of Scaling | Yang et al. (2022) muP; Muennighoff et al. (2023); Hoffmann et al. (2022); Hägele et al. (2024) |
| 4 | Beyond Attention: State-Space and Linear-Time Models | Gu et al. (2022) S4; Gu & Dao (2023) Mamba; Dao & Gu (2024) Mamba-2; Arora et al. (2024) Zoology |
| 5 | Diffusion and Flow-Based Generative Models | Ho et al. (2020); Song et al. (2021); Lipman et al. (2023) Flow matching; Peebles & Xie (2023) DiT; Sahoo et al. (2024) |
| 6 | Mechanistic Interpretability | Elhage et al. (2022) Superposition; Bricken et al. (2023); Templeton et al. (2024); Meng et al. (2022) ROME; Zou et al. (2023) RepE |
| 7 | Alignment Theory and Scalable Oversight | Gao et al. (2023) RM overoptimization; Bai et al. (2022) Constitutional AI; Irving et al. (2018) Debate; Burns et al. (2023) |
| 8 | Midterm: Research Proposal Defence | Proposal guidelines and review rubric |
| 9 | Reasoning Models and Reinforcement Learning at Scale | DeepSeek-AI (2025) DeepSeek-R1; Snell et al. (2024); Lightman et al. (2023); Turpin et al. (2023); Yue et al. (2025) |
| 10 | World Models and Embodied Foundation Models | Hafner et al. (2023) DreamerV3; Assran et al. (2023) I-JEPA; Bruce et al. (2024) Genie; Kim et al. (2024) OpenVLA; Black et al. (2024) pi0 |
| 11 | Frontier Multimodal Foundation Models | Chameleon Team (2024); Zhou et al. (2024) Transfusion; Défossez et al. (2024) Moshi; Liang et al. (2022) Modality gap |
| 12 | Synthetic Data, Distillation and Self-Improvement | Zelikman et al. (2022) STaR; Shumailov et al. (2024) Model collapse; Gerstgrasser et al. (2024); Yuan et al. (2024) |
| 13 | Open-Ended Agents and AI for Science | Jimenez et al. (2024) SWE-bench; Romera-Paredes et al. (2024) FunSearch; Novikov et al. (2025) AlphaEvolve; Lu et al. (2024) AI Scientist |
| 14 | Evaluation Science, Privacy and Trustworthy AI | Carlini et al. (2021) Extraction; Kirchenbauer et al. (2023) Watermark; Zheng et al. (2023) LLM-as-a-judge; Maini et al. (2024) TOFU |
| 15 | Final Research Presentations | Final paper guidelines and rubric |
Course Schedule (All Sections)
| Section | Type | Day 1 | Venue 1 | Day 2 | Venue 2 |
|---|---|---|---|---|---|
| CS622.1 | Course | Thursday 17:00 - 19:50 | B F1.16 | - | - |
Office Hours & Room
| Day | Time | Office | Notes |
|---|---|---|---|
| Monday | 11:00 - 15:00 | A F2.6 | |
| Thursday | 11:00 - 15:00 | A F2.6 |
Assessment Methods and Criteria
Assessment Components
Final research paper and presentation
AI: Consult InstructorAlignment with Learning Outcomes : 1 2 4 5
Written paper reviews (conference format)
AI: Consult InstructorAlignment with Learning Outcomes : 1 2 3
Paper presentation and leading the discussion
AI: Consult InstructorAlignment with Learning Outcomes : 2 3
Reproduction study of a recent paper
AI: Consult InstructorAlignment with Learning Outcomes : 2 4
Research proposal and defence (Week 8)
AI: Consult InstructorAlignment with Learning Outcomes : 3 5
Participation in seminar discussions
AI: Not AllowedAlignment with Learning Outcomes : 3
IUS Grading System
| Grading Scale | IUS Grading System | IUS Coeff. | Letter (B&H) | Numerical (B&H) |
|---|---|---|---|---|
| 0 - 44 | F | 0 | F | 5 |
| 45 - 54 | E | 1 | ||
| 55 - 64 | C | 2 | E | 6 |
| 65 - 69 | C+ | 2.3 | D | 7 |
| 70 -74 | B- | 2.7 | ||
| 75 - 79 | B | 3 | C | 8 |
| 80 - 84 | B+ | 3.3 | ||
| 85 - 94 | A- | 3.7 | B | 9 |
| 95 - 100 | A | 4 | A | 10 |
Late Work Policy
Information about late submission policies will be shared during class and posted in this section. Please check back for official guidelines.
ECTS Credit Calculation
📚 Student Workload
This 6 ECTS credit course corresponds to 150 hours of total student workload, distributed as follows:
Lectures and research seminars (in class)
45 hours ⏳ (15 week × 3 h)
Reading assigned papers and writing reviews
28 hours ⏳ (14 week × 2 h)
Preparation of paper presentations
12 hours ⏳ (2 week × 6 h)
Reproduction study
20 hours ⏳ (1 week × 20 h)
Original research project (proposal, experiments, paper)
45 hours ⏳ (15 week × 3 h)
150 Total Workload Hours
6 ECTS Credits
Course Policies
Academic Integrity
All work submitted must be your own. Plagiarism, cheating, or any form of academic dishonesty will result in disciplinary action according to university policies. When in doubt about citation practices, consult the instructor.
Attendance Policy
Students are expected to adhere to the attendance requirements as outlined in the International University of Sarajevo Study Rules and Regulations. Excessive absences, whether excused or unexcused, may impact academic performance and eligibility for assessment. Mandatory sessions (e.g., labs, workshops) require attendance unless formally exempted. For detailed policies on absences, documentation, and penalties, please refer to the official university regulations.
Technology & AI Policy
Laptops/tablets may be used for note-taking only during lectures. Phones should be silenced and put away during all class sessions. Audio/video recording requires prior permission from the instructor.
Artificial Intelligence (AI) Usage: The use of AI tools (e.g., ChatGPT, Copilot, Gemini) varies by assessment component. Please refer to the AI usage indicator next to each assessment item in the Assessment Methods and Criteria section above. Submitting AI-generated content as your own work, where AI is not explicitly allowed, constitutes an academic integrity violation.
Communication Policy
All course-related communication should occur through official university channels (institutional email or SIS). Emails should include [CS622] in the subject line.
Academic Quality Assurance Policy
Course Academic Quality Assurance is achieved through Semester Student Survey. At the end of each academic year, the institution of higher education is obliged to evaluate work of the academic staff, or the success of realization of the curricula.
Learning Tips
Be prepared to contribute thoughtfully during class discussions, labs, or collaborative work. Active participation deepens understanding and encourages critical thinking.
Complete assigned readings or prep materials before class. Take notes, highlight key ideas, and jot down questions. Aim to grasp core concepts and their applications—not just facts.
Use course frameworks or methodologies to analyze problems, case studies, or projects. Begin early to allow time for reflection and refinement. Seek feedback to improve your work.
Don’t hesitate to reach out when something is unclear. Use office hours, discussion boards, or peer networks to clarify concepts and stay on track.
Syllabus Last Updated on Oct 10, 2026 | International University of Sarajevo
Print Syllabus
Referencing Curricula Print this page
| Course Code | Course Title | Weekly Hours* | ECTS | Weekly Class Schedule | ||||||
| T | P | |||||||||
| CS622 | Advanced Methods in Artificial Intelligence | 3 | 0 | 6 | ||||||
| Prerequisite | None | It is a prerequisite to | - | |||||||
| Lecturer | Ali Almisreb | Office Hours / Room / Phone | Monday: 11:00-15:00 Thursday: 11:00-15:00 |
|||||||
| aalmisreb@ius.edu.ba | ||||||||||
| Assistant | Assistant E-mail | |||||||||
| Course Objectives | This doctoral course builds on CS511 Advanced Artificial Intelligence (large language models, vision-language models and agents) and moves to the research frontier: the theory behind why foundation models work, alternative architectures and generative paradigms, interpretability and alignment, reasoning and world models, and the science of evaluation. Each week combines a technical lecture (derivations and the key results of recent papers) with critical reading of primary literature. Students write peer reviews, reproduce a recent paper, and carry out an original research project aimed at a workshop or conference submission. Learning outcomes. On successful completion, students will be able to: Analyse the theoretical foundations of foundation models: expressivity, in-context learning, optimization and scaling, and the mathematics of diffusion/flow and state-space models. Apply and critically assess frontier methods in interpretability, alignment, reasoning, world models and multimodal learning, including their assumptions and failure modes. Critically review recent research papers at the standard of a programme committee member and identify open problems. Reproduce a published result and design rigorous experiments with sound statistical analysis and compute-aware ablations. Formulate, execute and communicate an original research contribution as a paper suitable for submission to a peer-reviewed venue. |
|||||||||
| Textbook | Prince, S. J. D. Understanding Deep Learning. MIT Press, 2023. Online: https://udlbook.github.io/udlbook/ Bishop, C. M., & Bishop, H. Deep Learning: Foundations and Concepts. Springer, 2024. Murphy, K. P. Probabilistic Machine Learning: Advanced Topics. MIT Press, 2023. Online: https://probml.github.io/pml-book/book2.html Primary research literature: a curated reading list of recent papers (NeurIPS, ICML, ICLR, ACL, CVPR and arXiv) distributed each week. | |||||||||
| Additional Literature |
|
|||||||||
| Learning Outcomes | After successful completion of the course, the student will be able to: | |||||||||
| Teaching Methods | The course is run as a research seminar. Each week the instructor presents the technical background and derivations; students read the assigned primary papers in advance, submit a structured review of one paper in conference format (summary, strengths, weaknesses, questions, score), and one student leads the discussion. Students reproduce the main result of a recent paper and conduct an original research project, individually or in pairs, with the goal of a workshop or conference submission. Research progress is discussed in individual meetings with the instructor. | |||||||||
| Teaching Method Delivery | Face-to-face | Teaching Method Delivery Notes | ||||||||
| WEEK | TOPIC | REFERENCE | ||||||||
| Week 1 | Research Methodology for Frontier AI | Lipton & Steinhardt (2019) Troubling trends in ML scholarship; Dodge et al. (2019) Show your work | ||||||||
| Week 2 | Theory of Transformers and In-Context Learning | Garg et al. (2022); von Oswald et al. (2023); Olsson et al. (2022); Merrill & Sabharwal (2024); Schaeffer et al. (2023) | ||||||||
| Week 3 | Optimization and the Science of Scaling | Yang et al. (2022) muP; Muennighoff et al. (2023); Hoffmann et al. (2022); Hägele et al. (2024) | ||||||||
| Week 4 | Beyond Attention: State-Space and Linear-Time Models | Gu et al. (2022) S4; Gu & Dao (2023) Mamba; Dao & Gu (2024) Mamba-2; Arora et al. (2024) Zoology | ||||||||
| Week 5 | Diffusion and Flow-Based Generative Models | Ho et al. (2020); Song et al. (2021); Lipman et al. (2023) Flow matching; Peebles & Xie (2023) DiT; Sahoo et al. (2024) | ||||||||
| Week 6 | Mechanistic Interpretability | Elhage et al. (2022) Superposition; Bricken et al. (2023); Templeton et al. (2024); Meng et al. (2022) ROME; Zou et al. (2023) RepE | ||||||||
| Week 7 | Alignment Theory and Scalable Oversight | Gao et al. (2023) RM overoptimization; Bai et al. (2022) Constitutional AI; Irving et al. (2018) Debate; Burns et al. (2023) | ||||||||
| Week 8 | Midterm: Research Proposal Defence | Proposal guidelines and review rubric | ||||||||
| Week 9 | Reasoning Models and Reinforcement Learning at Scale | DeepSeek-AI (2025) DeepSeek-R1; Snell et al. (2024); Lightman et al. (2023); Turpin et al. (2023); Yue et al. (2025) | ||||||||
| Week 10 | World Models and Embodied Foundation Models | Hafner et al. (2023) DreamerV3; Assran et al. (2023) I-JEPA; Bruce et al. (2024) Genie; Kim et al. (2024) OpenVLA; Black et al. (2024) pi0 | ||||||||
| Week 11 | Frontier Multimodal Foundation Models | Chameleon Team (2024); Zhou et al. (2024) Transfusion; Défossez et al. (2024) Moshi; Liang et al. (2022) Modality gap | ||||||||
| Week 12 | Synthetic Data, Distillation and Self-Improvement | Zelikman et al. (2022) STaR; Shumailov et al. (2024) Model collapse; Gerstgrasser et al. (2024); Yuan et al. (2024) | ||||||||
| Week 13 | Open-Ended Agents and AI for Science | Jimenez et al. (2024) SWE-bench; Romera-Paredes et al. (2024) FunSearch; Novikov et al. (2025) AlphaEvolve; Lu et al. (2024) AI Scientist | ||||||||
| Week 14 | Evaluation Science, Privacy and Trustworthy AI | Carlini et al. (2021) Extraction; Kirchenbauer et al. (2023) Watermark; Zheng et al. (2023) LLM-as-a-judge; Maini et al. (2024) TOFU | ||||||||
| Week 15 | Final Research Presentations | Final paper guidelines and rubric | ||||||||
| Assessment Methods and Criteria | Evaluation Tool | Quantity | Weight | Alignment with LOs | AI Usage |
| Final research paper and presentation | 1 | 40 | 1,2,4,5 | Consult Instructor | |
| Semester Evaluation Components | |||||
| Written paper reviews (conference format) | 10 | 15 | 1,2,3 | Consult Instructor | |
| Paper presentation and leading the discussion | 2 | 15 | 2,3 | Consult Instructor | |
| Reproduction study of a recent paper | 1 | 15 | 2,4 | Consult Instructor | |
| Research proposal and defence (Week 8) | 1 | 10 | 3,5 | Consult Instructor | |
| Participation in seminar discussions | 14 | 5 | 3 | Not Allowed | |
| *** ECTS Credit Calculation *** | |||||
| Activity | Hours | Weeks | Student Workload Hours | Activity | Hours | Weeks | Student Workload Hours | |||
| Lectures and research seminars (in class) | 3 | 15 | 45 | Reading assigned papers and writing reviews | 2 | 14 | 28 | |||
| Preparation of paper presentations | 6 | 2 | 12 | Reproduction study | 20 | 1 | 20 | |||
| Original research project (proposal, experiments, paper) | 3 | 15 | 45 | |||||||
| Total Workload Hours = | 150 | |||||||||
| *T= Teaching, P= Practice | ECTS Credit = | 6 | ||||||||
| Course Academic Quality Assurance: Semester Student Survey | Last Update Date: 06/10/2026 | |||||||||