Skip to content

Commit 766a27a

Browse files
Liby99Liby99
committed
Adding presentation page
1 parent 88cfe01 commit 766a27a

File tree

1 file changed

+111
-10
lines changed

1 file changed

+111
-10
lines changed

‎presentation.html‎

Lines changed: 111 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -39,21 +39,122 @@ <h1>EN.601.727 Machine Programming</h1>
3939
<main>
4040
<section>
4141
<h2>Oral Presentations</h2>
42+
</section>
43+
44+
</main>
45+
<main>
46+
<section>
47+
<h3>Sign-Up</h3>
48+
<p>
49+
We’ll have <strong>student-led presentation sessions</strong> starting from Week 9 of the semester.
50+
Each session will focus on one research topic with three related papers.
51+
You’ll form a <strong>group of three students</strong>, with each student presenting
52+
<strong>one paper</strong> (≈ 15–20 min talk + 5–10 min Q&amp;A).
53+
</p>
54+
<p>
55+
Please fill out the <a href="https://docs.google.com/forms/d/e/1FAIpQLSdunsLnTo26IlROU7QvEz52BFMnvSePlP7-_yqY1xaiRWOiIA/viewform" target="_blank">Google Form here</a>
56+
to rank your topic preferences. I’ll use these responses to form balanced groups and
57+
avoid race conditions.
58+
</p>
59+
<p><strong>Deadline:</strong> Friday, <strong>Oct 10 at 11:59 PM</strong></p>
60+
61+
<h3>Grading Policy</h3>
62+
<p>
63+
This oral presentation is <strong>graded on a completion basis</strong>, contributing
64+
<strong>10%</strong> of your final course grade:
65+
</p>
66+
<ul>
67+
<li><strong>2%</strong> for submitting the sign-up form before the deadline</li>
68+
<li><strong>8%</strong> for successfully completing your oral presentation</li>
69+
</ul>
70+
<p>
71+
<strong>Important:</strong> If you do <strong>not</strong> submit the form by the
72+
deadline, you’ll be <strong>automatically assigned</strong> to a topic and presentation slot
73+
at the instructor’s discretion. Failure to present in your assigned slot without prior approval
74+
will result in a <strong>zero for the presentation component</strong>.
75+
</p>
76+
<h3>Attendance Notice</h3>
77+
<p>
78+
Attendance during the student-led sessions will be <strong>recorded strictly</strong>.
79+
If you must miss a session due to external circumstances, please notify
80+
<strong>the instructor or the TA in advance</strong>.
81+
</p>
82+
</section>
83+
84+
</main>
85+
<main>
86+
87+
<section id="paper-topics">
88+
<h2>Paper Presentation Topics</h2>
89+
<p>
90+
Each student group will be assigned one of the following topics for their paper presentation.
91+
The exact papers can be coordinated between the group members and the instructor.
92+
As a start, the instructor will propose at least five papers per topic. You are encouraged
93+
to choose papers from this list, though you may also select papers that you find particularly
94+
exciting. To ease your preparation, you may choose papers that already have slides or videos
95+
available online.
96+
</p>
97+
98+
<h3>Topic 1. Language Models for Programming: Pretraining, Fine-Tuning, and Adaptation</h3>
99+
<p>
100+
This topic explores how large language models acquire and specialize programming knowledge.
101+
We’ll discuss pretraining objectives (next-token prediction, span corruption), fine-tuning strategies
102+
(instruction tuning, reinforcement learning, human and logical feedback), and parameter-efficient
103+
adaptation methods such as LoRA and quantization. We’ll also look at dataset construction for code
104+
understanding and synthesis, and evaluation benchmarks for measuring program synthesis capability.
105+
</p>
106+
107+
<h3>Topic 2. LLM Agents and Multi-Agent Frameworks</h3>
108+
<p>
109+
This topic focuses on how LLMs become agents that plan, communicate, and use tools.
110+
We’ll study communication protocols, tool interfaces, and multi-agent coordination frameworks,
111+
as well as real-world implementations such as LangChain, LangGraph, AutoGen, Swarm, Codex,
112+
Claude Code, and Cursor. Discussion will include agent design principles, tool selection and
113+
orchestration, and applications in collaborative programming, debugging, and long-horizon automation.
114+
</p>
115+
116+
<h3>Topic 3. Search-Based and Evolutionary Program Synthesis</h3>
117+
<p>
118+
This topic investigates how search and optimization drive program synthesis.
119+
We’ll cover genetic programming, Monte-Carlo search, Bayesian optimization, and self-improving loops
120+
for evolving programs or repair candidates. We will touch on works such as AlphaEvolve, and explore
121+
connections between search and neural synthesis, such as reinforcement-learning-based code refinement
122+
and hybrid LLM-guided search.
123+
</p>
124+
125+
<h3>Topic 4. Applications in Software Engineering and Security</h3>
126+
<p>
127+
This topic explores how synthesis techniques can automate or enhance software engineering tasks.
128+
We’ll cover testing and property-based testing, fuzzing, program analysis (static, dynamic, symbolic),
129+
vulnerability detection, exploit and proof-of-concept generation, specification and invariant synthesis,
130+
and program verification. Students may explore the application of LLM coders to both symbolic approaches
131+
(e.g., symbolic execution, constraint solving) and modern neural-assisted tools for security and reliability.
132+
</p>
133+
134+
<h3>Topic 5. Applications in Planning and Cyber-Physical Systems</h3>
42135
<p>
43-
Oral presentations are a key component of this course, worth 10% of your grade.
44-
They provide an opportunity to develop communication skills and share insights with your peers.
45-
Each presentation will be 25 minutes total, including ~15 minutes for the presentation and ~10 minutes for questions.
136+
This topic investigates synthesis for physical and hybrid systems that interact with the real world.
137+
We’ll examine planning languages (PDDL, Z3 encodings), reward-function synthesis for robot training,
138+
CAD and shape program generation, and robot configuration or simulation environment synthesis.
139+
Connections to autonomous system design, motion planning, and neurosymbolic control are also encouraged.
46140
</p>
141+
142+
<h3>Topic 6. Applications in Logic, Mathematics, and Theorem Proving</h3>
47143
<p>
48-
We will start the presentation from the 6th week of the course.
49-
You can sign up for a presentation slot by filling out a <a href="#" target="_blank">signup sheet</a>.
50-
Each student can sign up for topics; each topic can be presented by at most 2 students.
51-
Students can then choose specific papers to present from the list of topics.
144+
This topic covers program synthesis for symbolic reasoning and formal domains.
145+
We’ll study logic programming languages (Prolog, Datalog), first-order and temporal logic,
146+
and theorem-proving environments such as Lean, Coq, and Rocq. Applications include AI4Math and AI4Science,
147+
autoformalization, automated proof synthesis, and LLMs for mathematical reasoning or competition-level problem solving.
52148
</p>
149+
150+
<h3>Topic 7. Applications in Databases and Data-Wrangling Programs</h3>
53151
<p>
54-
The presentation is graded on a completion basis.
55-
You will receive a full score if you properly present the material in class.
56-
Extra credit will be given for exceptional presentations.
152+
This topic examines program synthesis for data analysis and manipulation tasks.
153+
We’ll discuss data-wrangling program generation (e.g., FlashFill, AutoPandas), SQL and NoSQL query synthesis,
154+
database optimization and migration, and automatic code generation for data collection and cleaning.
155+
Connections to natural-language interfaces for databases and dataflow-oriented program synthesis are also welcome.
156+
We’ll also discuss extensions of database-style query systems to new areas such as program analysis (e.g., CodeQL)
157+
and knowledge-graph reasoning.
57158
</p>
58159
</section>
59160
</main>

0 commit comments

Comments
 (0)