activity
20182022
most citedTest-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

112 citations · 211 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG20211 cited

Reinforcement Learning in Factored Action Spaces using Tensor Decompositions

Anuj Mahajan, Mikayel Samvelyan, Lei Mao +6

We present an extended abstract for the previously published work TESSERACT [Mahajan et al., 2021], which proposes a novel solution for Reinforcement Learning (RL) in large, factor…

cs.LG2020

Active Learning under Label Shift

Eric Zhao, Anqi Liu, Animashree Anandkumar +1

We address the problem of active learning under label shift: when the class proportions of source and target domains differ. We introduce a "medial distribution" to incorporate a t…

cs.LG2020

Causal Discovery in Physical Systems from Videos

Yunzhu Li, Antonio Torralba, Animashree Anandkumar +2

Causal discovery is at the core of human cognition. It enables us to reason about the environment and make counterfactual predictions about unseen scenarios that can vastly differ…

cs.LG2020

Convolutional Tensor-Train LSTM for Spatio-temporal Learning

Jiahao Su, Wonmin Byeon, Jean Kossaifi +3

Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation.However, existing methods s…

cs.LG2019

Learning Pose Estimation for UAV Autonomous Navigation andLanding Using Visual-Inertial Sensor Data

Francesca Baldini, Animashree Anandkumar, Richard M. Murray

In this work, we propose a new learning approach for autonomous navigation and landing of an Unmanned-Aerial-Vehicle (UAV). We develop a multimodal fusion of deep neural architectu…

cs.LG2019

Compositional Generalization with Tree Stack Memory Units

Forough Arabshahi, Zhichu Lu, Pranay Mundra +2

We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain. Standard neural networks fail to a large extent…