MAS.S60 How2AI | Schedule

** Exact topics and schedule subject to change, based on student interests and course discussions. **

Date	Topics	Readings
2/4	Week 1 Introduction [slides] Course syllabus and requirements Introduction to AI and AI research	Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions Multimodal Machine Learning: A Survey and Taxonomy Representation Learning: A Review and New Perspectives
2/6	Week 1 Introduction to AI Research [slides] Introduction to AI and AI research Generating ideas, reading and writing papers, AI experimentation
2/11	Week 2 Foundation 1: Data, structure, information [slides] Common data modalities Data collection strategies Training objectives and generalization	Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions
2/14	Week 2 Foundation 2: Practical AI tools [slides] Getting started with PyTorch Huggingface packages Debugging machine learning models
2/18	Week 3 No class, shifted President's day
2/20	Week 3 Project proposal presentations
2/25	Week 4 Foundation 3: Common model architectures Structure and invariances Temporal sequence models Spatial convolution models Models for sets and graphs	Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
2/25	Week 4 Discussion 1: Learning and generalization
3/4	Week 5 Multimodal 1: Connections and alignment Heterogeneity, connections, and interactions Multimodal technical challenges Alignment and transformers	Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions What Makes for Good Views for Contrastive Learning? Characterization and classification of semantic image-text relations When and why vision-language models behave like bags-of-words, and what to do about it?
3/6	Week 5 Discussion 2: Specialized vs general-purpose models
3/11	Week 6 Multimodal 2: Interactions and fusion Cross-modal interactions Multimodal fusion	Ten Myths of Multimodal Interaction Multimodal interaction: A review Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework Does my multimodal model learn cross-modal interactions? It’s harder to tell than you might think!
3/13	Week 6 Discussion 3: Multimodal interactions
3/18	Week 7 Multimodal 3: Cross-modal transfer Cross-modal learning via fusion Cross-modal learning via alignment Cross-modal learning via translation
3/20	Week 7 Discussion 4: Cross-modal learning
3/25	Week 8 No class, spring break
4/1	Week 9 Large models 1: Large Foundation Models Pre-training data Self-supervised learning Fine-tuning, instructing, alignment
4/3	Week 9 Project midterm presentations
4/8	Week 10 No class, member's week
4/15	Week 11 Large models 2: Large multimodal models Multimodal pre-training Adapting large language models to multimodal Multimodal LLMs with generation
4/17	Week 11 Discussion 5: Large language models
4/22	Week 12 Large models 3: Modern generative models Diffusion models Controllable generation
4/24	Week 12 Discussion 6: Large multimodal models
4/29	Week 13 Interaction 1: Interactive agents and reasoning WebAgent platforms Multi-step reasoning
5/1	Week 13 Discussion 7: Generative AI
5/6	Week 14 Interaction 2: Embodied AI Reinforcement learning Tangible and embodied systems Real-world considerations
5/8	Week 14 Project final presentations
5/13	Week 15 Interaction 3: Human AI interaction Interaction mediums Human in the loop learning Safety and reliability