Alert button
Picture for Brian Cheung

Brian Cheung

Alert button

How to guess a gradient

Dec 07, 2023
Utkarsh Singhal, Brian Cheung, Kartik Chandra, Jonathan Ragan-Kelley, Joshua B. Tenenbaum, Tomaso A. Poggio, Stella X. Yu

Viaarxiv icon

Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks

May 15, 2023
Minyoung Huh, Brian Cheung, Pulkit Agrawal, Phillip Isola

Figure 1 for Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
Figure 2 for Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
Figure 3 for Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
Figure 4 for Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
Viaarxiv icon

System identification of neural systems: If we got it right, would we know?

Feb 13, 2023
Yena Han, Tomaso Poggio, Brian Cheung

Figure 1 for System identification of neural systems: If we got it right, would we know?
Figure 2 for System identification of neural systems: If we got it right, would we know?
Figure 3 for System identification of neural systems: If we got it right, would we know?
Figure 4 for System identification of neural systems: If we got it right, would we know?
Viaarxiv icon

Meta-Learning and Self-Supervised Pretraining for Real World Image Translation

Dec 22, 2021
Ileana Rugina, Rumen Dangovski, Mark Veillette, Pooya Khorrami, Brian Cheung, Olga Simek, Marin Soljačić

Figure 1 for Meta-Learning and Self-Supervised Pretraining for Real World Image Translation
Figure 2 for Meta-Learning and Self-Supervised Pretraining for Real World Image Translation
Figure 3 for Meta-Learning and Self-Supervised Pretraining for Real World Image Translation
Figure 4 for Meta-Learning and Self-Supervised Pretraining for Real World Image Translation
Viaarxiv icon

Equivariant Contrastive Learning

Oct 28, 2021
Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, Marin Soljačić

Figure 1 for Equivariant Contrastive Learning
Figure 2 for Equivariant Contrastive Learning
Figure 3 for Equivariant Contrastive Learning
Figure 4 for Equivariant Contrastive Learning
Viaarxiv icon

Recurrent Parameter Generators

Jul 15, 2021
Jiayun Wang, Yubei Chen, Stella X. Yu, Brian Cheung, Yann LeCun

Figure 1 for Recurrent Parameter Generators
Figure 2 for Recurrent Parameter Generators
Figure 3 for Recurrent Parameter Generators
Figure 4 for Recurrent Parameter Generators
Viaarxiv icon

The Low-Rank Simplicity Bias in Deep Networks

Mar 18, 2021
Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung, Pulkit Agrawal, Phillip Isola

Figure 1 for The Low-Rank Simplicity Bias in Deep Networks
Figure 2 for The Low-Rank Simplicity Bias in Deep Networks
Figure 3 for The Low-Rank Simplicity Bias in Deep Networks
Figure 4 for The Low-Rank Simplicity Bias in Deep Networks
Viaarxiv icon

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

Aug 15, 2020
Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, Dinesh Jayaraman

Figure 1 for Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Figure 2 for Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Figure 3 for Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Figure 4 for Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Viaarxiv icon

Word Embedding Visualization Via Dictionary Learning

Oct 09, 2019
Juexiao Zhang, Yubei Chen, Brian Cheung, Bruno A Olshausen

Figure 1 for Word Embedding Visualization Via Dictionary Learning
Figure 2 for Word Embedding Visualization Via Dictionary Learning
Figure 3 for Word Embedding Visualization Via Dictionary Learning
Figure 4 for Word Embedding Visualization Via Dictionary Learning
Viaarxiv icon

Superposition of many models into one

Feb 14, 2019
Brian Cheung, Alex Terekhov, Yubei Chen, Pulkit Agrawal, Bruno Olshausen

Figure 1 for Superposition of many models into one
Figure 2 for Superposition of many models into one
Figure 3 for Superposition of many models into one
Figure 4 for Superposition of many models into one
Viaarxiv icon