research
∙
06/27/2023
Learning from Invalid Data: On Constraint Satisfaction in Generative Models
Generative models have demonstrated impressive results in vision, langua...
share
research
∙
02/07/2023
3D Neural Embedding Likelihood for Robust Sim-to-Real Transfer in Inverse Graphics
A central challenge in 3D scene perception via inverse graphics is robus...
research
∙
02/06/2023
Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design
Deep generative models, such as Variational Autoencoders (VAEs), Generat...
research
∙
08/30/2022
LINKS: A dataset of a hundred million planar linkage mechanisms for data-driven kinematic design
In this paper, we introduce LINKS, a dataset of 100 million one degree o...
research
∙
08/04/2022
Solving the Baby Intuitions Benchmark with a Hierarchically Bayesian Theory of Mind
To facilitate the development of new models to bridge the gap between ma...
research
∙
07/07/2022
Finding Fallen Objects Via Asynchronous Audio-Visual Integration
The way an object looks and sounds provide complementary reflections of ...
research
∙
10/30/2021
3DP3: 3D Scene Perception via Probabilistic Programming
We present 3DP3, a framework for inverse graphics that uses inference in...
research
∙
10/19/2021
Incorporating Rich Social Interactions Into MDPs
Much of what we do as humans is engage socially with other agents, a ski...
research
∙
03/25/2021
The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI
We introduce a visually-guided and physics-driven task-and-motion planni...
research
∙
02/24/2021
AGENT: A Benchmark for Core Psychological Reasoning
For machine agents to successfully interact with humans in real-world se...
research
∙
11/07/2020
Template Controllable keywords-to-text Generation
This paper proposes a novel neural model for the understudied task of ge...
research
∙
10/25/2020
Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modelling
Current autoencoder-based disentangled representation learning methods a...
research
∙
07/09/2020
ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation
We introduce ThreeDWorld (TDW), a platform for interactive multi-modal p...
research
∙
11/19/2019
SimVAE: Simulator-Assisted Training forInterpretable Generative Models
This paper presents a simulator-assisted training method (SimVAE) for va...
research
∙
11/01/2019
Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding
An event happening in the world is often made of different activities an...
research
∙
09/10/2019