Publications

AI For Science

Exploring Torsional Conformer Space with Physical Prior Mean Function-Driven Meta-Gaussian Processes. (Journal of Chemical Physics, 2023) [paper] Chong Teng, Daniel Huang, Elizabeth Donahue, and Junwei Lucas Bao.

On Training Derivative-Constrained Neural Networks. (Arxiv, 2023) [preprint] [code]
Kai Chieh Lo and Daniel Huang.

A Spur to Molecular Geometry Optimization: Gradient-Enhanced Universal Kriging with On-the-Fly Adaptive Ab Initio Prior Mean Functions in Curvilinear Coordinates. (Journal of Chemical Physics, Emerging Investigators Special Collection, 2023) [paper]
Chong Teng, Daniel Huang, and Junwei Lucas Bao.

Dual-Level Training of Gaussian Processes with Physically Inspired Priors for Geometry Optimizations. (Journal of Chemical Theory and Computation, 2022) [paper]
Chong Teng, Yang Wang, Daniel Huang, Katherine Martin, Jean-Baptiste Tristan, and Junwei Lucas Bao.

Geometry Meta-Optimization. (Journal of Chemical Physics, 2022) [paper]
Daniel Huang, Junwei Lucas Bao, and Jean-Baptiste Tristan.

mad-GP: Automatic Differentiation of Gaussian Processes for Molecules and Materials. (Journal of Mathematical Chemistry, 2022) [paper]
Daniel Huang, Chong Teng, Junwei Lucas Bao, and Jean-Baptiste Tristan.

Segmentation Fusion for Connectomics. (International Conference on Computer Vision, 2011) [paper]
Amelio Vazquez-Reina, Michael Gelbart, Daniel Huang, Jeff Lichtman, Eric Miller, and Hanspeter Pfister.

AI For Math

Elementary Logic in Linear Space. (Preprint, 2020) [preprint]
Daniel Huang.

On Learning to Prove. (Preprint, 2019) [preprint]
Daniel Huang.

GamePad: A Learning Environment for Theorem Proving. (International Conference on Learning Representations, 2019) [paper] [gamepad]
Daniel Huang, Prafulla Dhariwal, Dawn Song, and Ilya Sutskever.

Probabilistic Programming

Push: Concurrent Probabilistic Programming for Bayesian Deep Learning. (Arxiv, 2023) [preprint] [Push]
Daniel Huang, Chris Camano, Jonathan Tsegaye, and Jonathan Austin Gale.

An Application of Computable Distributions to the Semantics of Probabilistic Programs. (Chapter in Foundations of Probabilistic Programming, 2020) [chapter]
Daniel Huang, Bas Spitters, and Greg Morrisett.

Compiling Markov Chain Monte Carlo Algorithms for Probabilistic Modeling. (Programming Language Design and Implementation, 2017) [paper] [augurv2]
Daniel Huang, Jean-Baptiste Tristan, and Greg Morrisett.

An Application of Computable Distributions to the Semantics of Probabilistic Programming Languages. (European Symposium on Programming, 2016, EAPLS Best Paper) [paper]
Daniel Huang and Greg Morrisett.

Augur: Data-parallel Probabilistic Modeling. (Neural Information Processing Systems, 2014, Spotlight) [paper]
Jean-Baptiste Tristan, Daniel Huang, Joseph Tassarotti, Adam Pocock, Stephen Greene, and Guy Steele.

Quantum Computing

Quantum Computing and Visualization: A Disruptive Technological Change Ahead. (IEEE Computer Graphics and Applications, 43(6), Nov/Dec, 2023) [paper]
E. Wes Bethel, Mercy G. Amankwah, Jan Balewski, Roel Van Beeumen, Daan Camps, Daniel Huang, and Talita Perciano.

Formal Verification

Formalizing the SAFECode Type System. (Certified Proofs and Programs, 2013) [paper] [vsafecode]
Daniel Huang and Greg Morrisett.