Alert button
Picture for Pavel Sountsov

Pavel Sountsov

Alert button

Robust Inverse Graphics via Probabilistic Inference

Feb 02, 2024
Tuan Anh Le, Pavel Sountsov, Matthew D. Hoffman, Ben Lee, Brian Patton, Rif A. Saurous

Viaarxiv icon

Training Chain-of-Thought via Latent-Variable Inference

Nov 28, 2023
Du Phan, Matthew D. Hoffman, David Dohan, Sholto Douglas, Tuan Anh Le, Aaron Parisi, Pavel Sountsov, Charles Sutton, Sharad Vikram, Rif A. Saurous

Viaarxiv icon

ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images

Oct 27, 2022
Matthew D. Hoffman, Tuan Anh Le, Pavel Sountsov, Christopher Suter, Ben Lee, Vikash K. Mansinghka, Rif A. Saurous

Figure 1 for ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images
Figure 2 for ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images
Figure 3 for ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images
Figure 4 for ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images
Viaarxiv icon

Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC

Jun 12, 2020
Erik Nijkamp, Ruiqi Gao, Pavel Sountsov, Srinivas Vasudevan, Bo Pang, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC
Figure 2 for Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC
Figure 3 for Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC
Figure 4 for Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC
Viaarxiv icon

tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware

Feb 04, 2020
Junpeng Lao, Christopher Suter, Ian Langmore, Cyril Chimisov, Ashish Saxena, Pavel Sountsov, Dave Moore, Rif A. Saurous, Matthew D. Hoffman, Joshua V. Dillon

Viaarxiv icon

NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport

Mar 09, 2019
Matthew Hoffman, Pavel Sountsov, Joshua V. Dillon, Ian Langmore, Dustin Tran, Srinivas Vasudevan

Figure 1 for NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
Figure 2 for NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
Figure 3 for NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
Figure 4 for NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
Viaarxiv icon

Length bias in Encoder Decoder Models and a Case for Global Conditioning

Sep 21, 2016
Pavel Sountsov, Sunita Sarawagi

Figure 1 for Length bias in Encoder Decoder Models and a Case for Global Conditioning
Figure 2 for Length bias in Encoder Decoder Models and a Case for Global Conditioning
Figure 3 for Length bias in Encoder Decoder Models and a Case for Global Conditioning
Figure 4 for Length bias in Encoder Decoder Models and a Case for Global Conditioning
Viaarxiv icon