40 citations · 103 across the 17 of their papers we have counts for
17 papers
Universal Neural Functionals
Allan Zhou, Chelsea Finn, James Harrison
A challenging problem in many modern machine learning tasks is to process weight-space features, i.e., to transform or extract information from the weights and gradients of a neura…
AutoFT: Learning an Objective for Robust Fine-Tuning
Caroline Choi, Yoonho Lee, Annie Chen +3
Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performan…
Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning
Evan Zheran Liu, Sahaana Suri, Tong Mu +2
Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of s…
Neural Functional Transformers
Allan Zhou, Kaien Yang, Yiding Jiang +5
The recent success of neural networks as implicit representation of data has driven growing interest in neural functionals: models that can process other neural networks as input b…
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
Katherine Tian, Eric Mitchell, Allan Zhou +5
A trustworthy real-world prediction system should produce well-calibrated confidence scores; that is, its confidence in an answer should be indicative of the likelihood that the an…
Permutation Equivariant Neural Functionals
Allan Zhou, Kaien Yang, Kaylee Burns +5
This work studies the design of neural networks that can process the weights or gradients of other neural networks, which we refer to as neural functional networks (NFNs). Despite…
NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis
Allan Zhou, Moo Jin Kim, Lirui Wang +2
Expert demonstrations are a rich source of supervision for training visual robotic manipulation policies, but imitation learning methods often require either a large number of demo…
Unsupervised language models for disease variant prediction
Allan Zhou, Nicholas C. Landolfi, Daniel C. O'Neill
There is considerable interest in predicting the pathogenicity of protein variants in human genes. Due to the sparsity of high quality labels, recent approaches turn to \textit{uns…
Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations
Xinyu Yang, Huaxiu Yao, Allan Zhou +1
There is an inescapable long-tailed class-imbalance issue in many real-world classification problems. Current methods for addressing this problem only consider scenarios where all…
Do Deep Networks Transfer Invariances Across Classes?
Allan Zhou, Fahim Tajwar, Alexander Robey +4
To generalize well, classifiers must learn to be invariant to nuisance transformations that do not alter an input's class. Many problems have "class-agnostic" nuisance transformati…
Policy Architectures for Compositional Generalization in Control
Allan Zhou, Vikash Kumar, Chelsea Finn +1
Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment. Learning goal-conditioned policies is a na…
Noether Networks: Meta-Learning Useful Conserved Quantities
Ferran Alet, Dylan Doblar, Allan Zhou +3
Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often explo…
Discriminator Augmented Model-Based Reinforcement Learning
Behzad Haghgoo, Allan Zhou, Archit Sharma +1
By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is…
Meta-Learning Symmetries by Reparameterization
Allan Zhou, Tom Knowles, Chelsea Finn
Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers…
Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
Allan Zhou, Eric Jang, Daniel Kappler +7
Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations.…
Cost Functions for Robot Motion Style
Allan Zhou, Anca D. Dragan
We focus on autonomously generating robot motion for day to day physical tasks that is expressive of a certain style or emotion. Because we seek generalization across task instance…
Expressive Robot Motion Timing
Allan Zhou, Dylan Hadfield-Menell, Anusha Nagabandi +1
Our goal is to enable robots to \emph{time} their motion in a way that is purposefully expressive of their internal states, making them more transparent to people. We start by inve…