2.3k citations · 2.5k across the 7 of their papers we have counts for
9 papers
Disentanglement via Latent Quantization
Kyle Hsu, Will Dorrell, James C. R. Whittington +2
In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the mode…
Vision-Based Manipulators Need to Also See from Their Hands
Kyle Hsu, Moo Jin Kim, Rafael Rafailov +2
We study how the choice of visual perspective affects learning and generalization in the context of physical manipulation from raw sensor observations. Compared with the more commo…
On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…
Differentiable Annealed Importance Sampling and the Perils of Gradient Noise
Guodong Zhang, Kyle Hsu, Jianing Li +2
Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation, but are not fully differentiable due to the use of Metropol…
On the role of data in PAC-Bayes bounds
Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh +2
The dominant term in PAC-Bayes bounds is often the Kullback--Leibler divergence between the posterior and prior. For so-called linear PAC-Bayes risk bounds based on the empirical r…
Unsupervised Curricula for Visual Meta-Reinforcement Learning
Allan Jabri, Kyle Hsu, Ben Eysenbach +3
In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. Howe…