2.3k citations · 2.7k across the 29 of their papers we have counts for
9 papers · 1 filter
Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data
Wai Tong Chung, Bassem Akoush, Pushan Sharma +9
Analysis of compressible turbulent flows is essential for applications related to propulsion, energy generation, and the environment. Here, we present BLASTNet 2.0, a 2.2 TB networ…
Codebook Features: Sparse and Discrete Interpretability for Neural Networks
Alex Tamkin, Mohammad Taufeeque, Noah D. Goodman
Understanding neural networks is challenging in part because of the dense, continuous nature of their hidden states. We explore whether we can train neural networks to have hidden…
Studying Large Language Model Generalization with Influence Functions
Roger Grosse, Juhan Bae, Cem Anil +14
When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which tr…
Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning
Alex Tamkin, Margalit Glasgow, Xiluo He +1
What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate…
Active Learning Helps Pretrained Models Learn the Intended Task
Alex Tamkin, Dat Nguyen, Salil Deshpande +2
Models can fail in unpredictable ways during deployment due to task ambiguity, when multiple behaviors are consistent with the provided training data. An example is an object class…
C5T5: Controllable Generation of Organic Molecules with Transformers
Daniel Rothchild, Alex Tamkin, Julie Yu +2
Methods for designing organic materials with desired properties have high potential impact across fields such as medicine, renewable energy, petrochemical engineering, and agricult…
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.…
Viewmaker Networks: Learning Views for Unsupervised Representation Learning
Alex Tamkin, Mike Wu, Noah Goodman
Many recent methods for unsupervised representation learning train models to be invariant to different "views," or distorted versions of an input. However, designing these views re…
Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy
Ramtin Keramati, Christoph Dann, Alex Tamkin +1
While maximizing expected return is the goal in most reinforcement learning approaches, risk-sensitive objectives such as conditional value at risk (CVaR) are more suitable for man…