(2023). SODA: Bottleneck Diffusion Models for Representation Learning. arXiv.


(2023). Evaluating VLMs for Score-Based, Multi-Probe Annotation of 3D Objects. arXiv.


(2021). SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition. NeurIPS 2021.

PDF Cite Animated figures

(2019). Spatial Broadcast Decoder: A simple architecture for learning disentangled representations in VAEs. ICLR 2019 Workshop on Learning from Limited Labeled Data.

PDF Cite

(2019). COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration. arXiv.

PDF Cite Code Twitter thread explainer

(2019). Multi-Object Representation Learning with Iterative Variational Inference. ICML 2019.

PDF Cite

(2019). MONet: Unsupervised Scene Decomposition and Representation. arXiv.

PDF Cite

(2018). Understanding disentangling in β-VAE. 2017 NIPS Workshop on Learning Disentangled Representations.

PDF Cite

(2017). DARLA: Improving zero-shot transfer in reinforcement learning. ICML 2017.

PDF Cite arXiv

(2017). SCAN: Learning Abstract Hierarchical Compositional Visual Concepts. arXiv.

PDF Cite DeepMind Blog

(2017). dSprites: Disentanglement testing Sprites dataset. Github.

Cite Dataset

(2017). β-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. ICLR 2017.

PDF Cite Dataset Paper