1

Probabilistically Rewired Message-Passing Neural Networks

ICLR 2024

Collapsed Inference for Bayesian Deep Learning

NeurIPS 2023     Oral Presentation at ICML 2023 Workshop on SPIGM (Top 5%)

A Unified Approach to Count-Based Weakly-Supervised Learning

NeurIPS 2023

A Unified Knowledge Distillation Framework for Deep Directed Graphical Models

CVPR 2023

SIMPLE: A Gradient Estimator for k-Subset Sampling

ICLR 2023

Tractable Computation of Expected Kernels

UAI 2021

Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations

NeurIPS 2020     Spotlight presentation, acceptance rate 280/9454 = 2.96%

Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing

ICML 2020

Efficient Search-Based Weighted Model Integration

UAI 2019

Stein Variational Message Passing for Continuous Graphical Models

ICML 2018