Search Results for author:
Found 17 papers, 7 papers with code
Universal Neural Functionals
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 neural network.
AutoFT: Learning an Objective for Robust Fine-Tuning
Given a task, AutoFT searches for a fine-tuning procedure that enhances out-of-distribution (OOD) generalization.
Robot Fleet Learning via Policy Merging
We show that FLEET-MERGE consolidates the behavior of policies trained on 50 tasks in the Meta-World environment, with good performance on nearly all training tasks at test time.
Neural Processing of Tri-Plane Hybrid Neural Fields
While processing a field with the same reconstruction quality, we achieve task performance far superior to frameworks that process large MLPs and, for the first time, almost on par with architectures handling explicit representations.
Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning
Specifically, we design an office navigation environment, where the agent's goal is to find a particular office, and office locations differ in different buildings (i. e., tasks).
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
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 answer is correct, enabling deferral to an expert in cases of low-confidence predictions.
NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis
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 demonstrations or expensive online expert supervision to learn reactive closed-loop behaviors.
Unsupervised language models for disease variant prediction
There is considerable interest in predicting the pathogenicity of protein variants in human genes.
Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations
We study this multi-domain long-tailed learning problem and aim to produce a model that generalizes well across all classes and domains.
Do Deep Networks Transfer Invariances Across Classes?
Based on this analysis, we show how a generative approach for learning the nuisance transformations can help transfer invariances across classes and improve performance on a set of imbalanced image classification benchmarks.
Ranked #22 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Policy Architectures for Compositional Generalization in Control
Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment.
Noether Networks: Meta-Learning Useful Conserved Quantities
Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases.
Discriminator Augmented Model-Based Reinforcement Learning
By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction.
Model-based Reinforcement Learning
reinforcement-learning
+1
Meta-Learning Symmetries by Reparameterization
We present a method for learning and encoding equivariances into networks by learning corresponding parameter sharing patterns from data.
Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards
Imitation learning allows agents to learn complex behaviors from demonstrations.
Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
Imitation learning allows agents to learn complex behaviors from demonstrations.
Cost Functions for Robot Motion Style
We focus on autonomously generating robot motion for day to day physical tasks that is expressive of a certain style or emotion.
Robotics
