Swarat Chaudhuri (@swarat) / X

Swarat Chaudhuri

1,688 posts

Swarat Chaudhuri

@swarat

Research Scientist at @GoogleDeepmind London, Professor at @UTCompSci. Automated Reasoning + Machine Learning + Programming Languages.

London, UK

cs.utexas.edu/~swarat

Joined June 2009

Pinned
Swarat Chaudhuri
@swarat
May 25
Delighted to finally unveil these results! 🎉 Many congratulations to the team, who worked tirelessly for almost a year to build and evaluate AlphaProof Nexus. We revised many priors during this project — most notably, we discovered that with current frontier models, simple
Pushmeet Kohli
@pushmeet
May 25
AI agents are advancing research-level math. 🚀 I’m thrilled to share @GoogleDeepMind’s AlphaProof Nexus - an agentic framework for formal proof search powered by Gemini. When applied to a set of open formal math problems, our agent autonomously solved: ✅ 9 open Erdős
29K
Swarat Chaudhuri
@swarat
Nov 2, 2021
Thrilled to release our NeurIPS '21 Spotlight, led by students Rohan Mukherjee and Yeming Wen: "Neural Program Generation Modulo Static Analysis". cs.utexas.edu/~swarat/pubs/n…. tl;dr: In program synthesis and related tasks, Codex/GPT is not all you need. (1/n)
Swarat Chaudhuri
@swarat
Feb 6, 2019
"We find that the effort researchers waste in writing proposals may be comparable to the total scientific value of the research that the funding supports, especially when only a few proposals can be funded." dx.plos.org/10.1371/journa…
Swarat Chaudhuri
@swarat
Mar 9, 2024
This paper (dl.acm.org/doi/10.1145/36…) has now been accepted at #TOPLAS and will appear at #PLDI24 as a journal-first presentation. Proud of @meghana_aparna's excellent work on this, and many thanks to my amazing collaborator Tom Reps! Let me now summarize why I am excited about
Swarat Chaudhuri
@swarat
Nov 15, 2022
Some CS papers are written over a few months -- some others, over a year. Our new Arxiv post, led by Tom Reps and @meghana_aparna, describes ideas developed over ~25 years. arxiv.org/abs/2211.06818 (1/n)🧵
dl.acm.org
CFLOBDDs: Context-Free-Language Ordered Binary Decision Diagrams | ACM Transactions on Programming...
This article presents a new compressed representation of Boolean functions, called CFLOBDDs (for Context-Free-Language Ordered Binary Decision Diagrams). They are essentially a plug-compatible...
18K
Swarat Chaudhuri
@swarat
Sep 12, 2019
It's official: I am moving to @UTCompSci in Spring 2020! @RiceCompSci is a wonderful department -- I owe a tremendous amount to my students, mentors, and collaborators here -- and Houston has a lot going for it too. But after eight years, it was time for a change.
Swarat Chaudhuri
@swarat
Nov 15, 2022
Some CS papers are written over a few months -- some others, over a year. Our new Arxiv post, led by Tom Reps and @meghana_aparna, describes ideas developed over ~25 years. arxiv.org/abs/2211.06818 (1/n)🧵
Swarat Chaudhuri
@swarat
Sep 28, 2020
Program induction is hard as search spaces of programs explode quickly. We have a new line of attack on this (to appear at #NeurIPS2020): using neural relaxations of discrete sets of programs as admissible heuristics. Paper: arxiv.org/abs/2007.12101. Code: github.com/trishullab/near.
Swarat Chaudhuri
@swarat
Jul 17, 2024
Delighted to announce PutnamBench, a new AI-for-math benchmark for evaluating neural theorem provers for Coq, Lean, and Isabelle on Putnam math competition problems. Almost all the problems here are beyond the reach of current approaches. Excellent leadership by @gtsoukal, who
George Tsoukalas
@gtsoukal
Jul 17, 2024
Announcing PutnamBench: an evaluation benchmark for formal mathematical reasoning in Lean 4, Isabelle, and Coq! PutnamBench consists of problems from the William-Lowell Putnam Mathematical Competition, the premier collegiate mathematics exam in the US & Canada. 🧵
9.5K
Swarat Chaudhuri
@swarat
Dec 23, 2021
We had a lot of fun writing this survey! Thank you, @rupakmajumdar, for inviting us to write this. You can find a free excerpt here: nowpublishers.com/article/Downlo… Below, a 🧵on what neurosymbolic programming (NSP) is and why we think it's important. (1/n)
🇺🇦 Alex Polozov
@Skiminok
Dec 20, 2021
Hey, ML/PL enthusiasts! Looking for some "light" reading for the holiday break? FnT just published our survey on "Neurosymbolic Programming", written jointly with @swarat, Kevin Ellis, @rishabhs, Armando Solar-Lezama, and @yisongyue. nowpublishers.com/article/Detail…
Swarat Chaudhuri
@swarat
Sep 8, 2018
1) This is a thread on our #NIPS2018 paper (@lazarvalkov et al.; preliminary version at arxiv.org/abs/1804.00218), and more broadly, about the role of language abstractions in deep learning (DL).
arxiv.org
HOUDINI: Lifelong Learning as Program Synthesis
We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning. Reusing high-level concepts across domains and learning complex...
Swarat Chaudhuri
@swarat
Mar 31, 2024
Replying to @ylecun
That review makes some basic mistakes.
Jonathan Haidt
@JonHaidt
Mar 31, 2024
A review in Nature, by @candice_odgers, asserts that I have mistaken correlation for causation and that “there is no evidence that using these platforms is rewiring children’s brains or driving an epidemic of mental illness.” Both of these assertions are untrue.
16K
Swarat Chaudhuri
@swarat
Jan 13, 2023
Our Neurosymbolic Programming tutorial is coming to #POPL23! We'll explain the basics, do an algorithmic deep dive, and explore neuroscience applications. * 1/16 (Mon), 2 pm * Speakers: Armando, my student Atharva, me (@yisongyue & @JenJSun in spirit). popl23.sigplan.org/details/POPL-2…
10K
Swarat Chaudhuri
@swarat
Jun 10, 2024
The @neurosym summer school is off to a great start! In the morning, @atharva_sehgal, @akavidemic, and I gave the first part of our tutorial on neurosymbolic programming. Slides at drive.google.com/file/d/1lgk5W3…. Now @AI4Code is telling us about the Scallop framework for
9K
Swarat Chaudhuri
@swarat
May 10, 2024
The neurosymbolic learning meetup at #ICLR2024 was a big success! Many thanks to all who showed up — and especially to @theo_olausson, who made the event happen.
11K