Sumith Kulal

Biography

I am a fourth-year PhD student in Computer Science at Stanford University. I'm grateful to be co-advised by Alex Aiken and Jiajun Wu and am affiliated with the Stanford Vision and Learning lab. My research interests are in computer vision and machine learning. Currently, I'm focusing on video understanding and human motion analysis and synthesis. My research is supported by the Brown Institute for Media Innovation.

I am always up for a conversation, let's catch up if you are around!

Projects

• motion2prog: Representing human motion with programs.
• shape2prog: Representing 3D shapes with programs.
• SPoC: Search-based Pseudocode to Code.
• BFSS: Blazing Fast Skolem Synthesis.
• Syncro: Automatic Incrementalization through Synthesis.
• Orb: Resource Bounds Verifier for Functional Scala programs.
• tusSAT: A hardware based (VHDL) SAT solver.
• verify-xv6: Verification of buffer cache properties in xv6.
• SymPy: Computer Algebra System written in pure Python.
• SymEngine: Fast symbolic manipulation library written in C++.

Publications

Programmatic Concept Learning for Human Motion Description and Synthesis

Sumith Kulal^*, Jiayuan Mao^*, Alex Aiken+, Jiajun Wu+.

CVPR 2022  

Hierarchical Motion Uderstanding via Motion Programs

Sumith Kulal^*, Jiayuan Mao^*, Alex Aiken, Jiajun Wu.

CVPR 2021  

Boolean Functional Synthesis: Hardness and Practical Algorithms^*

S. Akshay, Supratik Chakraborty, Shubham Goel, Sumith Kulal, Shetal Shah.
FMSD 2020  

SPoC: Search-based Pseudocode to Code

Sumith Kulal^*, Panupong Pasupat^*, Kartik Chandra, Mina Lee, Oded Padon,
Alex Aiken, Percy Liang.
NeurIPS 2019

Scalable Synthesis with Symbolic Syntax Graphs

Rohin Shah, Sumith Kulal, Rastislav Bodik.
SYNT 2018  [slides] 

What's hard about Boolean Functional Synthesis?^*

S. Akshay, Supratik Chakraborty, Shubham Goel, Sumith Kulal, Shetal Shah.
CAV 2018  

Contract-based Resource Verification for Higher-order Functions with Memoization

Ravichandhran Madhavan, Sumith Kulal, Viktor Kuncak.
POPL 2017  

SymPy: Symbolic computing in Python

SymPy Development Team.
PeerJ CS 2016  

Tech Reports/Seminar

Pushing The Envelope for Boolean Function Synthesis^*

S. Akshay, Supratik Chakraborty, Shubham Goel, Sumith Kulal, Shetal Shah.
CSE IITB Technical Report  

Space Leaks Exploration in Haskell

Sumith Kulal, Rupanshu Ganvir, Suresh Sudhakaran.
Seminar Report, Spring 2017  

^* All authors contributed equally.

Services

PC Member

• 2022: CVPR, ICLR, ICML
• 2017: SciPy, Austin TX

Connections

Many thanks to Shumo Chu for the site inspiration.