306 citations · 371 across the 10 of their papers we have counts for
10 papers
Scalable Optimization in the Modular Norm
Tim Large, Yang Liu, Minyoung Huh +3
To improve performance in contemporary deep learning, one is interested in scaling up the neural network in terms of both the number and the size of the layers. When ramping up the…
The Platonic Representation Hypothesis
Minyoung Huh, Brian Cheung, Tongzhou Wang +1
We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multip…
Training Neural Networks from Scratch with Parallel Low-Rank Adapters
Minyoung Huh, Brian Cheung, Jeremy Bernstein +2
The scalability of deep learning models is fundamentally limited by computing resources, memory, and communication. Although methods like low-rank adaptation (LoRA) have reduced th…
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
Minyoung Huh, Brian Cheung, Pulkit Agrawal +1
This work examines the challenges of training neural networks using vector quantization using straight-through estimation. We find that a primary cause of training instability is t…
Totems: Physical Objects for Verifying Visual Integrity
Jingwei Ma, Lucy Chai, Minyoung Huh +4
We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene. Totems…
Learning to Ground Multi-Agent Communication with Autoencoders
Toru Lin, Minyoung Huh, Chris Stauffer +2
Communication requires having a common language, a lingua franca, between agents. This language could emerge via a consensus process, but it may require many generations of trial a…
The Low-Rank Simplicity Bias in Deep Networks
Minyoung Huh, Hossein Mobahi, Richard Zhang +3
Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has ask…
Transforming and Projecting Images into Class-conditional Generative Networks
Minyoung Huh, Richard Zhang, Jun-Yan Zhu +2
We present a method for projecting an input image into the space of a class-conditional generative neural network. We propose a method that optimizes for transformation to countera…
Fighting Fake News: Image Splice Detection via Learned Self-Consistency
Minyoung Huh, Andrew Liu, Andrew Owens +1
Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging pro…
What makes ImageNet good for transfer learning?
Minyoung Huh, Pulkit Agrawal, Alexei A. Efros
The tremendous success of ImageNet-trained deep features on a wide range of transfer tasks begs the question: what are the properties of the ImageNet dataset that are critical for…