Albert Wilcox

I am a PhD student in the Georgia Tech School of Interactive Computing studying machine learning and robotics. I am advised by Professor Animesh Garg. I'm also currently interning with the Microsoft Spatial AI Lab and Computer Vision and Geometry Group at ETH Zurich, advised by Oier Mees and Professor Marc Pollefeys.

Previously I did my BA and MS at BAIR with Professor Ken Goldberg. I've also spent time with Nuro and AWS.

Beyond research, I enjoy outdoor activities of any sort, climbing, playing guitar/bass, and endurance sports (I was on Berkeley's triathlon team). Feel free to follow me on Strava!

Email / Resume / Google Scholar / Twitter / Github / LinkedIn

Research

I'm interested in methods for deploying learned robot policies in new settings. This may mean quickly adapting to a new embodiment, generalizing to an unseen scene, or reasoning through an unknown task.

Specifically, I'm looking into imitation learning from 3D scene representations, large multimodal models (VLAs), VLA reasoning, and scaling with simulated data. Lately I'm particularly interested in using large-scale synthetic data to improve spatial understanding.

Always happy to chat about research, so feel free to reach out!

	MESA: An Evaluation Framework for Compositional, Semantic, and Spatial Generalization in Robotics Albert Wilcox, Frank Chang, Aishani Chakraborty, Nhi Nguyen, Jeremy A. Collins, Vaibhav Saxena, Benjamin Joffe, Siddharth Karamcheti, Animesh Garg. Preprint, 2026. Website / Bibtex @article{mesa2026, title={MESA: An Evaluation Framework for Compositional, Semantic, and Spatial Generalization in Robotics}, author={Albert Wilcox and Frank Chang and Aishani Chakraborty and Nhi Nguyen and Jeremy A. Collins and Vaibhav Saxena and Benjamin Joffe and Siddharth Karamcheti and Animesh Garg}, journal={arXiv preprint}, year={2026} } A dynamic evaluation framework for precise, reproducible measurement of language-conditioned policy generalization, isolating in-distribution performance and four axes of generalization: spatial configuration, object instance, object category, and subtask composition.
	AMPLIFY: Actionless Motion Priors for Robot Learning from Videos Jeremy A. Collins, Loránd Cheng, Kunal Aneja, Albert Wilcox, Benjamin Joffe, Animesh Garg. International Conference on Robotics and Automation (ICRA), 2026. PDF / Website / Code / Bibtex @misc{collins2025amplify, title={AMPLIFY: Actionless Motion Priors for Robot Learning from Videos}, author={Jeremy A. Collins and Loránd Cheng and Kunal Aneja and Albert Wilcox and Benjamin Joffe and Animesh Garg}, year={2025}, eprint={2506.14198}, archivePrefix={arXiv}, primaryClass={cs.RO}, url={https://arxiv.org/abs/2506.14198}} A framework that leverages large-scale action-free video data by encoding visual dynamics into compact, discrete motion tokens from keypoint trajectories, decoupling learning what motion defines a task from how robots execute it.
	Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning Albert Wilcox, Mohamed Ghanem, Masoud Moghani, Pierre Barroso, Benjamin Joffe, Animesh Garg. Conference on Robot Learning (CoRL), 2025. PDF / Website / Bibtex @misc{wilcox2025adapt3r, title={Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning}, author={Albert Wilcox and Mohamed Ghanem and Masoud Moghani and Pierre Barroso and Benjamin Joffe and Animesh Garg}, year={2025}, eprint={2503.04877}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2503.04877}} An imitation learning algorithm utilizing 3D scene representations to enable zero-shot transfer to novel embodiments and camera poses.
	QueST: Self-Supervised Skill Abstractions for Learning Continuous Control Atharva Mete, Haotian Xue, Albert Wilcox, Yongxin Chen, Animesh Garg. Conference on Neural Information Processing Systems (NeurIPS), 2024. PDF / Website / Bibtex @misc{mete2024questselfsupervisedskillabstractions, title={QueST: Self-Supervised Skill Abstractions for Learning Continuous Control}, author={Atharva Mete and Haotian Xue and Albert Wilcox and Yongxin Chen and Animesh Garg}, year={2024}, eprint={2407.15840}, archivePrefix={arXiv}, primaryClass={cs.RO}, url={https://arxiv.org/abs/2407.15840}} A novel multitask and fewshot behavior cloning algorithm which first learns to tokenize continuous robot action sequences before using an autoregressive transformer to learn a policy in the token space.
	Self-Supervised Visuo-Tactile Pretraining to Locate and Follow Garment Features Justin Kerr, Huang Huang, Albert Wilcox, Ryan Hoque, Jeffrey Ichnowski, Roberto Calandra, and Ken Goldberg. Robotics Science and Systems (RSS), 2023. PDF / Website / Bibtex @misc{kerr2023selfsupervisedvisuotactilepretraininglocate, title={Self-Supervised Visuo-Tactile Pretraining to Locate and Follow Garment Features}, author={Justin Kerr and Huang Huang and Albert Wilcox and Ryan Hoque and Jeffrey Ichnowski and Roberto Calandra and Ken Goldberg}, year={2023}, eprint={2209.13042}, archivePrefix={arXiv}, primaryClass={cs.RO}, url={https://arxiv.org/abs/2209.13042}} Learning a shared latent space between visual and tactile observations which is useful for a variety of downstream tasks.
	Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations Albert Wilcox, Ashwin Balakrishna, Daniel Brown, Jules Dedieu, Wyame Benslimane, Ken Goldberg Conference on Neural Information Processing Systems (NeurIPS), 2022. PDF / Website / Bibtex @inproceedings{wilcox2022monte, title={Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations}, author={Albert Wilcox and Ashwin Balakrishna and Jules Dedieu and Wyame Benslimane and Daniel S. Brown and Ken Goldberg}, booktitle={Advances in Neural Information Processing Systems}, editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho}, year={2022}, url={https://openreview.net/forum?id=FLzTj4ia8BN} } An easy-to-implement change that can be made to any off-policy actor critic algorithm to speed up and stabilize sparse reward deep reinforcement learning from demonstrations.
	Learning to Localize, Grasp and Hand Over Unmodified Surgical Needles Albert Wilcox, Justin Kerr, Brijen Thananjeyan, Jeff Ichnowski, Minho Hwang, Samuel Paradis, Danyal Fer, Ken Goldberg IEEE International Conference on Robotics and Automation (ICRA), 2022. PDF / Website / Bibtex @inproceedings{9812393, author={Wilcox, Albert and Kerr, Justin and Thananjeyan, Brijen and Ichnowski, Jeffrey and Hwang, Minho and Paradis, Samuel and Fer, Danyal and Goldberg, Ken}, booktitle={2022 International Conference on Robotics and Automation (ICRA)}, title={Learning to Localize, Grasp, and Hand Over Unmodified Surgical Needles}, year={2022}, pages={9637-9643}, doi={10.1109/ICRA46639.2022.9812393} } An algorithm combining active sensing, perception and imitation learning to reliably hand unmodified surgical needles from one arm to the other on a daVinci Research Kit surgical robot.
	LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks Albert Wilcox, Ashwin Balakrishna, Brijen Thananjeyan, Joseph E. Gonzalez, Ken Goldberg Conference on Robot Learning (CoRL) 2021. PDF / Website / Bibtex @inproceedings{LS3, title={LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks}, author={Wilcox, Albert and Balakrishna, Ashwin and Thananjeyan, Brijen and Gonzalez, Joseph E. and Goldberg, Ken}, booktitle={Conference on Robot Learning (CoRL)}, year={2021}, organization={PMLR} } Safe and efficient RL from image observations by leveraging suboptimal demonstrations to structure exploration and examples of constraint violations to satisfy user-specified constraints.
	ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning Ryan Hoque, Ashwin Balakrishna, Ellen Novoseller, Daniel S. Brown, Albert Wilcox, Ken Goldberg Conference on Robot Learning (CoRL) 2021. Oral Presentation (6.5% of papers). PDF / Website / Bibtex @inproceedings{thrifty, title={ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning}, author={Hoque, Ryan and Balakrishna, Ashwin and Novoseller, Ellen and Brown, Daniel S. and Wilcox, Albert and Goldberg, Ken}, booktitle={Conference on Robot Learning (CoRL)}, year={2021}, organization={PMLR} } An interactive imitation learning algorithm that reasons about both state novelty and risk to actively query for human interventions. The algorithm balances supervisor burden and task performance more successfully than prior robot-gated algorithms and is competitive with an oracle human-gated baseline.
	Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning Nathan O Lambert, Albert Wilcox, Howard Zhang, Kristofer SJ Pister, Roberto Calandra IEEE Conference on Decision and Control (CDC) 2021. PDF / Website / Bibtex @article{lambert2020learning, title={Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning}, author={Lambert, Nathan O and Wilcox, Albert and Zhang, Howard and Pister, Kristofer SJ and Calandra, Roberto}, journal={arXiv preprint arXiv:2012.09156}, year={2020} } Reframing the model-based RL framework with long-term rather than single step state predictions using continuous "trajectory-based" models.

As with the other 90% of budding ML researchers, I got my website template from Jon Barron.