Schedule

Below is the tentative schedule for the course. The schedule is subject to change at any time.

Week	Date	Topic	Presenter	Comment
		SE Basics
Week 1	24-Aug-26	Intro and Course Details	Saikat
	26-Aug-26	Program Analysis 1	Saikat
Week 2	31-Aug-26	Program Analysis 2	Saikat
	2-Sep-26	Software Testing	Saikat
Week 3	7-Sep-26	No Classes (labor day)
	9-Sep-26	Security	Saikat
		LLM Basics
Week 4	14-Sep-26	ML Models: Intro	Saikat	Project Proposal Due
	16-Sep-26	Post-Training LLM Adaptation	Saikat
Week 5	21-Sep-26	Fine-Tuning/Quantization	Saikat
	23-Sep-26	LLM Agents (for SE)	Saikat
Week 6	28-Sep-26	Proposal Presentations
	30-Sep-26	Agent Architectures
Week 7	5-Oct-26	Evaluation of LLMs
	7-Oct-26	Speculative Decoding/Alignment
		Flexible and Efficient Grammar-Constrained Decoding
		Enforcing Temporal Constraints for LLM Agents
Week 8	12-Oct-26	No classes (Fall Break)
	14-Oct-26	Security of Agents
		Securing AI Agents With Information-Flow Control
		Efficient and Sound Probabilistic Verification for AI Agents
Week 9	19-Oct-26	LLM/Agent Adaptation		MidTerm Report Due
		Training software engineering agents and verifiers with swe-gym
		Specbench: Measuring reward hacking in long-horizon coding agents
	21-Oct-26	Dynamic Analysis
		Faster runtime verification during testing via feedback-guided selective monitoring
		SHERLOC: Structured Diagnostic Localization for Code Repair Agents
Week 10	26-Oct-26	Flaky Tests
		Understanding and Improving Flaky Test Classification
		TERA: Optimizing Stochastic Regression Tests in Machine Learning Projects
	28-Oct-26	Verification
		Cobblestone: A Divide-and-Conquer Approach for Automating Formal Verification
		AutoVerus: Automated Proof Generation for Rust Code
		SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification
Week 11	2-Nov-26	Code Translation
		Scalable, Validated Code Translation of Entire Projects using Large Language Models
		ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories
		SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging
		Verifier-Guided Code Translation via Meta-Step Decoding
	4-Nov-26	Security
		CyberGym: Evaluating AI Agents’ Real-World Cybersecurity Capabilities at Scale
		KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
Week 12	9-Nov-26	Specification Inference
		SpecGen: Automated Generation of Formal Program Specifications via Large Language Models
		Specula: Scaling formal specifications for autonomous model checking of system code
	11-Nov-26	Fuzzing
		Fuzzing with Agents? Generators Are All You Need
		Agentic Predicates Reasoning for Directed Fuzzing
Week 13	16-Nov-26	Debugging DL Training
		Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks
		TrainVerify: Equivalence-Based Verification for Distributed LLM Training
	18-Nov-26	GPU Kernels Testing/Verification
		TensorRight: Automated Verification of Tensor Graph Rewrites
		Hunting CUDA Bugs at Scale with cuFuzz
Week 14	23-Nov-26	Testing DL Libraries and Compilers
		Testing Deep Learning Libraries via Neurosymbolic Constraint Learning
		Bootstrapping Fuzzers for Compilers of Low-Resource Language Dialects Using Language Models
	25-Nov-26	No Classes (Thanksgiving Break)
Week 15	30-Nov-26	Project Presentations
	2-Dec-26	Project Presentations
Week 16	7-Dec-26	Project Presentations
	9-Dec-26	No Classes		Final Report Due