Research

Interests

Deep (embodied, multi-agent) reinforcement learning, representation learning from interaction, causality, nonparametric multivariate dependence testing, algebraic statistics.

Selected Publications

For a full list of publications see my Google Scholar or Semantic Scholar author page.

	Towards Disturbance-Free Visual Mobile Manipulation Tianwei Ni, Kiana Ehsani, Luca Weihs, and Jordi Salvador (2021) See Python package on GitHub

	The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents Sarah Pratt, Luca Weihs, and Ali Farhadi (2022)

	Bridging the Imitation Gap by Adaptive Insubordination Luca Weihs, Unnat Jain, Iou-Jen Liu, Jordi Salvador, et al. (2021) Published in NeurIPS'21. See Python package on GitHub

	Simple but Effective: CLIP Embeddings for Embodied AI Apoorv Khandelwal, Luca Weihs, Roozbeh Mottaghi, and Aniruddha Kembhavi (2021) Under review.

	Visual Room Rearrangement Luca Weihs, Matt Deitke, Aniruddha Kembhavi, and Roozbeh Mottaghi (2021) Accepted for publication in CVPR'21. See Python package on GitHub

	Learning Generalizable Visual Representations via Interactive Gameplay Luca Weihs, Aniruddha Kembhavi, Kiana Ehsani, Sarah M Pratt, et al. (2021) Published in ICLR'21.

	AllenAct Luca Weihs, Jordi Salvador, Klemen Kotar, Unnat Jain, et al. (2020) See Python package on GitHub

	A Cordial Sync: Going Beyond Marginal Policies For Multi-Agent Embodied Tasks Unnat Jain, Luca Weihs, Eric Kolve, Ali Farhadi, et al. (2020) Published in ECCV. See Python package on GitHub

	Two Body Problem: Collaborative Visual Task Completion Unnat Jain, Luca Weihs, Eric Kolve, Mohammad Rastegari, et al. (2019) Published in CVPR. See Python package on GitHub

	Symmetric Rank Covariances: a Generalised Framework for Nonparametric Measures of Dependence Luca Weihs, Mathias Drton, and Nicolai Meinshausen (2018) Published in Biometrika. See R package on GitHub

	Nested Covariance Determinants and Restricted Trek Separation in Gaussian Graphical Models Mathias Drton, Elina Robeva, and Luca Weihs (2018) Published in Bernoulli.

	Learning to Predict Citation-Based Impact Measures Luca Weihs and Oren Etzioni (2017) Published in JCDL'17. See Python package on GitHub

	Determinantal Generalizations of Instrumental Variables Luca Weihs, Bill Robinson, Emilie Dufresne, Jennifer Kenkel, et al. (2017) Published in Journal of Causal Inference. See R package on GitHub

	Marginal likelihood and model selection for Gaussian latent tree and forest models Mathias Drton, Shaowei Lin, Luca Weihs, and Piotr Zwiernik (2017) Published in Bernoulli. See R package on CRAN and GitHub

	Large-Sample Theory for the Bergsma-Dassios Sign Covariance Preetam Nandy, Luca Weihs, and Mathias Drton (2016) Published in the EJS. See R package on CRAN and GitHub

	Generic Identifiability of Linear Structural Equation Models by Ancestor Decomposition Mathias Drton and Luca Weihs (2016) Published in the Scandinavian Journal of Statistics. See R package on CRAN and GitHub

	Efficient Computation of the Bergsma-Dassios Sign Covariance Luca Weihs, Mathias Drton, and Dennis Leung (2016) Published in Computational Statistics. See R package on CRAN and GitHub

Projects

Revisiting Recursive Inversion Models for Permutations Luca Weihs (2015) PhD Prelim Project See R package on GitHub