Search Results for author:
Found 11 papers, 9 papers with code
Identifying the Risks of LM Agents with an LM-Emulated Sandbox
Alongside the emulator, we develop an LM-based automatic safety evaluator that examines agent failures and quantifies associated risks.
Evaluating Self-Supervised Learning via Risk Decomposition
Our decomposition consists of four error components: approximation, representation usability, probe generalization, and encoder generalization.
Improving Self-Supervised Learning by Characterizing Idealized Representations
For non-contrastive learning, we use our framework to derive a simple and novel objective.
Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning
The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditional image-only methods.
Learning Instance-Specific Augmentations by Capturing Local Invariances
We introduce InstaAug, a method for automatically learning input-specific augmentations from data.
Optimal Representations for Covariate Shift
Machine learning systems often experience a distribution shift between training and testing.
Ranked #37 on
Image Classification
on ObjectNet
(using extra training data)
Lossy Compression for Lossless Prediction
Most data is automatically collected and only ever "seen" by algorithms.
Ranked #1 on
Image Compression
on ImageNet
(using extra training data)
Learning Optimal Representations with the Decodable Information Bottleneck
We address the question of characterizing and finding optimal representations for supervised learning.
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
Stationary stochastic processes (SPs) are a key component of many probabilistic models, such as those for off-the-grid spatio-temporal data.
Location Attention for Extrapolation to Longer Sequences
We hypothesize that models with a separate content- and location-based attention are more likely to extrapolate than those with common attention mechanisms.
Convolutional Conditional Neural Processes
We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data.
