activity
20122024
most citedBayesian Posterior Sampling via Stochastic Gradient Fisher Scoring

111 citations · 187 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2024

Parallelized Spatiotemporal Binding

Gautam Singh, Yue Wang, Jiawei Yang +4

While modern best practices advocate for scalable architectures that support long-range interactions, object-centric models are yet to fully embrace these architectures. In particu…

cs.LG2024★ 3 cited

Simple Hierarchical Planning with Diffusion

Chang Chen, Fei Deng, Kenji Kawaguchi +2

Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in general…

cs.LG2023★ 4 cited

Facing Off World Model Backbones: RNNs, Transformers, and S4

Fei Deng, Junyeong Park, Sungjin Ahn

World models are a fundamental component in model-based reinforcement learning (MBRL). To perform temporally extended and consistent simulations of the future in partially observab…

cs.LG2023★ 7 cited

An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning

Jaesik Yoon, Yi-Fu Wu, Heechul Bae +1

Unsupervised object-centric representation (OCR) learning has recently drawn attention as a new paradigm of visual representation. This is because of its potential of being an effe…

cs.LG2021★ 11 cited

DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations

Fei Deng, Ingook Jang, Sungjin Ahn

Top-performing Model-Based Reinforcement Learning (MBRL) agents, such as Dreamer, learn the world model by reconstructing the image observations. Hence, they often fail to discard…

cs.LG2021★ 5 cited

Generative Video Transformer: Can Objects be the Words?

Yi-Fu Wu, Jaesik Yoon, Sungjin Ahn

Transformers have been successful for many natural language processing tasks. However, applying transformers to the video domain for tasks such as long-term video generation and sc…