Parallel Sampling of Diffusion Models
Andy Shih and Suneel Belkhale and Stefano Ermon and Dorsa Sadigh and Nima Anari
NeurIPS 2023 — 37th Conference on Neural Information Processing Systems, New Orleans, USA, December 2023.
[bib] [arxiv] [slides] [poster] [code]
Spotlight Presentation

Diverse Conventions for Human-AI Collaboration
Bidipta Sarkar and Andy Shih and Dorsa Sadigh
NeurIPS 2023 — 37th Conference on Neural Information Processing Systems, New Orleans, USA, December 2023.
[bib]

Long Horizon Temperature Scaling
Andy Shih and Dorsa Sadigh and Stefano Ermon
ICML 2023 — 40th International Conference on Machine Learning, Hawaii, USA, July 2023.
[bib] [arxiv] [pdf] [slides] [poster] [code]

Training and Inference on Any-Order Autoregressive Models the Right Way
Andy Shih and Dorsa Sadigh and Stefano Ermon
NeurIPS 2022 — 36th Conference on Neural Information Processing Systems, New Orleans, USA, December 2022.
[bib] [arxiv] [pdf] [slides] [poster] [code]
Oral Presentation [top 1.9%]
2023 UAI Workshop on Tractable Probabilistic Modeling Best Paper Honorable Mention

Imitation Learning by Estimating Expertise of Demonstrators
Mark Beliaev* and Andy Shih* and Stefano Ermon and Dorsa Sadigh and Ramtin Pedarsani
ICML 2022 — 39th International Conference on Machine Learning, Baltimore, USA, July 2022.
[bib] [arxiv] [pdf] [code]

Conditional Imitation Learning for Multi-Agent Games
Andy Shih and Stefano Ermon and Dorsa Sadigh
HRI 2022 — 17th ACM/IEEE International Conference on Human-Robot Interaction, Virtual, March 2022.
[bib] [arxiv] [pdf] [code]

PantheonRL: A MARL Library for Dynamic Training Interactions
Bidipta Sarkar* and Aditi Talati* and Andy Shih* and Dorsa Sadigh
AAAI 2022 (Demo Track) — 36th AAAI Conference on Artificial Intelligence (Demo Track), Virtual, February 2022.
[bib] [arxiv] [pdf] [code] [video]

On the Opportunities and Risks of Foundation Models
Co-author: Section 2.4 Reasoning and Search
Stanford Center for Research on Foundation Models (CRFM)
[report] [arxiv]

HyperSPNs: Compact and Expressive Probabilistic Circuits
Andy Shih and Dorsa Sadigh and Stefano Ermon
NeurIPS 2021 — 35th Conference on Neural Information Processing Systems, Virtual, December 2021.
[bib] [arxiv] [pdf] [slides] [poster] [code]

Influencing Towards Stable Multi-Agent Interactions
Woodrow Zhouyuan Wang and Andy Shih and Annie Xie and Dorsa Sadigh
CoRL 2021 — Proceedings of the 5th Conference on Robot Learning, London, UK, November 2021.
[bib] [arxiv] [pdf]

On the Critical Role of Conventions in Adaptive Human-AI Collaboration
Andy Shih and Arjun Sawhney and Jovana Kondic and Stefano Ermon and Dorsa Sadigh
ICLR 2021 — 9th International Conference on Learning Representations, Virtual, May 2021.
[bib] [arxiv] [pdf] [slides] [poster] [code] [blogpost]

Probabilistic Circuits for Variational Inference in Discrete Graphical Models
Andy Shih and Stefano Ermon
NeurIPS 2020 — 34th Conference on Neural Information Processing Systems, Vancouver, Canada, December 2020.
[bib] [arxiv] [pdf] [slides] [poster] [code] [blogpost]

On Tractable Representations of Binary Neural Networks
Weijia Shi and Andy Shih and Adnan Darwiche and Arthur Choi
KR 2020 — 17th International Conference on Principles of Knowledge Representation and Reasoning, Rhodes, Greece, September 2020.
[bib] [arxiv] [pdf]

On Symbolically Encoding the Behavior of Random Forests
Arthur Choi and Andy Shih and Anchal Goyanka and Adnan Darwiche
FoMLAS 2020 — 3rd Workshop on Formal Methods for ML-Enabled Autonomous Systems, Virtual, July 2020.
[bib] [arxiv] [pdf]

Smoothing Structured Decomposable Circuits
Andy Shih and Guy Van den Broeck and Paul Beame and Antoine Amarilli
NeurIPS 2019 — 33rd Conference on Neural Information Processing Systems, Vancouver, Canada, December 2019.
[bib] [arxiv] [pdf] [slides] [poster] [code]
Spotlight Presentation [top 2.4%]

Explaining Classifiers
Andy Shih
Master's Thesis — UCLA Department of Computer Science, 2019.
[bib] [pdf]

Verifying Binarized Neural Networks by Angluin-Style Learning
Andy Shih and Adnan Darwiche and Arthur Choi
SAT 2019 — 22nd International Conference on Theory and Applications of Satisfiability Testing, Lisbon, Portugal, July 2019.
[bib] [pdf] [code]

Compiling Neural Networks into Tractable Boolean Circuits
Arthur Choi and Weijia Shi and Andy Shih and Adnan Darwiche
VNN 2019 — AAAI Spring Symposium on Verification of Neural Networks, Stanford University, USA, March 2019.
[bib] [pdf]

Compiling Bayesian Network Classifiers into Decision Graphs
Andy Shih and Arthur Choi and Adnan Darwiche
AAAI 2019 — 33rd AAAI Conference on Artificial Intelligence, Honolulu, USA, January 2019.
[bib] [pdf] [code]

Formal Verification of Bayesian Network Classifiers
Andy Shih and Arthur Choi and Adnan Darwiche
PGM 2018 — 9th International Conference on Probabilistic Graphical Models, Prague, Czech Republic, September 2018.
[bib] [pdf]

A Symbolic Approach to Explaining Bayesian Network Classifiers
Andy Shih and Arthur Choi and Adnan Darwiche
IJCAI 2018 — 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden, July 2018.
[bib] [arxiv] [pdf] [code]