publications

2026

1. PhysWM

   CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization

   Tewodros W. Ayalew, Matthew Jeung, Samuel Wheeler, and 5 more authors

   In CoRL Workshop PhysWM, 2026

   Takeaway: end-to-end continuous latent actions + diffusion world model from action-free video; 43% RoboDesk upright-block planning vs. 5% AdaWorld; 1.7/3.0 long-horizon real UR5 vs. 1.5 AdaWorld.

   Lightning Abs arXiv Project Page PDF

   Lightning talk at WM@Booth 2026. Also presented at the Midwest Robotics Workshop (MWRW) 2026.

   End-to-end continuous latent actions + diffusion world model from action-free video (incl. Something-Something V2). Supports imitation and MPC planning; 43% RoboDesk upright-block planning vs. 5% AdaWorld; 1.7/3.0 long-horizon real UR5 vs. 1.5 AdaWorld.

2. CoRL

   What Are We Actually Benchmarking in Robot Manipulation?

   Tianchong Jiang, Xiangshan Tan, Samuel Wheeler, and 3 more authors

   In Proceedings of the Conference on Robot Learning (CoRL), 2026

   Takeaway: four diagnostics showing popular manipulation benchmarks often fail as proxies for general capability; reference implementations released.

   Best Paper Finalist Abs arXiv Project Page PDF Code

   Best Paper Award finalist and oral presentation at CoRL 2026. Best Abstract Award at the IROS 2026 Workshop on Reproducible Benchmarking of Robotic Grasping and Manipulation.

   Four diagnostics (shortcut solvability, statistical significance, creeping overfitting, data-source dependence) showing popular manipulation benchmarks often fail as proxies for general capability.

2025

1. ICCV

   

   PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement

   Tewodros W. Ayalew, Xiao Zhang, Kevin Yuanbo Wu, and 3 more authors

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025

   Takeaway: self-supervised visual progress reward with online push-back; Meta-World RL without env reward; real-UR5 few-shot offline RL under noisy demos.

   Abs Project Page Code

   Self-supervised visual progress reward with adversarial online push-back. Pretrained on EPIC-KITCHENS; Meta-World RL without environment reward and real-UR5 few-shot offline RL under noisy demos, outperforming VIP/R3M-style rewards.

2. HRI

   

   Enabling End Users to Program Robots Using Reinforcement Learning

   Tewodros W. Ayalew, Jennifer Wang, Michael L. Littman, and 2 more authors

   In Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2025

2021

1. 

   Automatic Microplot Localization Using UAV images and a Hierarchical Image-based Optimization Method

   Sara Mardanisamani, Tewodros W. Ayalew, Minhajul Arfin Badhon, and 7 more authors

   Plant Phenomics, 2021

2020

1. 

   Unsupervised Domain Adaptation for Plant Organ Counting

   Tewodros W. Ayalew, Jordan Ubbens, and Ian Stavness

   In Proceedings of the European Conference on Computer Vision (ECCV), 2020

   Best Paper Project Page

   Best Paper Award at the ECCV 2020 CVPPP workshop.

2. 

   AutoCount: Unsupervised Segmentation and Counting of Organs in Field Images

   Jordan Ubbens, Tewodros W. Ayalew, Steve Shirtliffe, and 3 more authors

   In Proceedings of the European Conference on Computer Vision (ECCV), 2020