Jitendra Malik

Implicit Maximum Likelihood Estimation

2018 · arXiv (Cornell University)

Implicit probabilistic models are models defined naturally in terms of a sampling procedure and often induces a likelihood function that cannot be expressed explicitly. We develop a simple method for estimating parameters in implicit models …

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

2021 · arXiv (Cornell University)

We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We make comprehensive contributions to all levels of the embodied AI stack - data, simulation, …

Side-Tuning: A Baseline for Network Adaptation via Additive Side\n Networks

2019 · arXiv (Cornell University)

When training a neural network for a desired task, one may prefer to adapt a\npre-trained network rather than starting from randomly initialized weights.\nAdaptation can be useful in cases when training data is scarce, when a …