2.3k citations · 2.4k across the 17 of their papers we have counts for
18 papers
DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling
Linqi Zhou, Andy Shih, Chenlin Meng +1
Recent methods such as Score Distillation Sampling (SDS) and Variational Score Distillation (VSD) using 2D diffusion models for text-to-3D generation have demonstrated impressive g…
Diverse Conventions for Human-AI Collaboration
Bidipta Sarkar, Andy Shih, Dorsa Sadigh
Conventions are crucial for strong performance in cooperative multi-agent games, because they allow players to coordinate on a shared strategy without explicit communication. Unfor…
Parallel Sampling of Diffusion Models
Andy Shih, Suneel Belkhale, Stefano Ermon +2
Diffusion models are powerful generative models but suffer from slow sampling, often taking 1000 sequential denoising steps for one sample. As a result, considerable efforts have b…
Long Horizon Temperature Scaling
Andy Shih, Dorsa Sadigh, Stefano Ermon
Temperature scaling is a popular technique for tuning the sharpness of a model distribution. It is used extensively for sampling likely generations and calibrating model uncertaint…
Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding
William Chen, Siyi Hu, Rajat Talak +1
Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of a…
Training and Inference on Any-Order Autoregressive Models the Right Way
Andy Shih, Dorsa Sadigh, Stefano Ermon
Conditional inference on arbitrary subsets of variables is a core problem in probabilistic inference with important applications such as masked language modeling and image inpainti…
Imitation Learning by Estimating Expertise of Demonstrators
Mark Beliaev, Andy Shih, Stefano Ermon +2
Many existing imitation learning datasets are collected from multiple demonstrators, each with different expertise at different parts of the environment. Yet, standard imitation le…
Conditional Imitation Learning for Multi-Agent Games
Andy Shih, Stefano Ermon, Dorsa Sadigh
While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a…
PantheonRL: A MARL Library for Dynamic Training Interactions
Bidipta Sarkar, Aditi Talati, Andy Shih +1
We present PantheonRL, a multiagent reinforcement learning software package for dynamic training interactions such as round-robin, adaptive, and ad-hoc training. Our package is des…
HyperSPNs: Compact and Expressive Probabilistic Circuits
Andy Shih, Dorsa Sadigh, Stefano Ermon
Probabilistic circuits (PCs) are a family of generative models which allows for the computation of exact likelihoods and marginals of its probability distributions. PCs are both ex…
Influencing Towards Stable Multi-Agent Interactions
Woodrow Z. Wang, Andy Shih, Annie Xie +1
Learning in multi-agent environments is difficult due to the non-stationarity introduced by an opponent's or partner's changing behaviors. Instead of reactively adapting to the oth…
On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…
On the Critical Role of Conventions in Adaptive Human-AI Collaboration
Andy Shih, Arjun Sawhney, Jovana Kondic +2
Humans can quickly adapt to new partners in collaborative tasks (e.g. playing basketball), because they understand which fundamental skills of the task (e.g. how to dribble, how to…
Probabilistic Circuits for Variational Inference in Discrete Graphical Models
Andy Shih, Stefano Ermon
Inference in discrete graphical models with variational methods is difficult because of the inability to re-parameterize gradients of the Evidence Lower Bound (ELBO). Many sampling…
On Symbolically Encoding the Behavior of Random Forests
Arthur Choi, Andy Shih, Anchal Goyanka +1
Recent work has shown that the input-output behavior of some machine learning systems can be captured symbolically using Boolean expressions or tractable Boolean circuits, which fa…
On Tractable Representations of Binary Neural Networks
Weijia Shi, Andy Shih, Adnan Darwiche +1
We consider the compilation of a binary neural network's decision function into tractable representations such as Ordered Binary Decision Diagrams (OBDDs) and Sentential Decision D…
Smoothing Structured Decomposable Circuits
Andy Shih, Guy Van den Broeck, Paul Beame +1
We study the task of smoothing a circuit, i.e., ensuring that all children of a plus-gate mention the same variables. Circuits serve as the building blocks of state-of-the-art infe…
A Symbolic Approach to Explaining Bayesian Network Classifiers
Andy Shih, Arthur Choi, Adnan Darwiche
We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We…