Publications

Research Publications

My research focuses on perception, representation, and planning for robot manipulation. I work at the intersection of computer vision, machine learning, and robotics to develop systems that can better understand and interact with their environment.

RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains

Yi Ru Wang, Carter Ung, Evan Gubarev, Christopher Tan, Siddhartha Srinivasa, Dieter Fox

arXiv preprint

A language-driven evaluation framework that lets users author executable robotic manipulation tasks from natural language, compiled into reproducible task specifications.

📄 Paper 🌐 Website

RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation

Yi Ru Wang, Carter Ung, Grant Tannert, Jiafei Duan, Josephine Li, Amy Le, Rishabh Oswal, Markus Grotz, Wilbert Pumacay, Yuquan Deng, Ranjay Krishna, Dieter Fox, Siddhartha Srinivasa

ICRA 2026

A comprehensive evaluation framework for robotic manipulation tasks with structured and scalable assessment methods.

📄 Paper 🌐 Website

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

Jiafei Duan, Wilbert Pumacay, Nishanth Kumar, Yi Ru Wang, Shulin Tian, Wentao Yuan, Ranjay Krishna, Dieter Fox, Ajay Mandlekar, Yijie Guo

International Conference on Learning Representations (ICLR)

A vision-language model for detecting and reasoning over failures in robotic manipulation tasks.

📄 Paper 🌐 Website

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation

Haoquan Fang, Markus Grotz, Wilbert Pumacay, Yi Ru Wang, Dieter Fox, Ranjay Krishna, Jiafei Duan

International Conference on Machine Learning (ICML)

Integration of visual foundation models with memory architecture for enhanced robotic manipulation capabilities.

📄 Paper 🌐 Website

PointArena: Probing Multimodal Grounding Through Language-Guided Pointing

Long Cheng, Jiafei Duan, Yi Ru Wang, Haoquan Fang, Boyang Li, Yushan Huang, Elvis Wang, Ainaz Eftekhar, Jason Lee, Wentao Yuan, Rose Hendrix, Noah A. Smith, Fei Xia, Dieter Fox, Ranjay Krishna

In Submission

A framework for probing multimodal grounding through language-guided pointing interactions.

📄 Paper 🌐 Website

MolmoAct: Action Reasoning Models that can Reason in Space

Jason Lee, Jiafei Duan, Haoquan Fang, Yuquan Deng, Shuo Liu, Boyang Li, Bohan Fang, Jieyu Zhang, Yi Ru Wang, Sangho Lee, Winson Han, Wilbert Pumacay, Angelica Wu, Rose Hendrix, Karen Farley, Eli VanderBilt, Ali Farhadi, Dieter Fox, Ranjay Krishna

ICRA 2026

Action reasoning models with spatial reasoning capabilities for robotic manipulation tasks.

📄 Paper

Manipulate-Anything: Automating Real-World Robots using Vision-Language Models

Jiafei Duan*, Wentao Yuan*, Wilbert Pumacay, Yi Ru Wang, Kiana Ehsani, Dieter Fox, Ranjay Krishna

Conference on Robot Learning (CoRL)

Automation of real-world robots using vision-language models for manipulation tasks.

📄 Paper 🌐 Website

M

MVTrans: Multi-View Perception for Transparent Objects

Yi Ru Wang*, Yuchi Zhao*, Haoping Xu*, Alan Aspuru-Guzik, Florian Shkurti, Animesh Garg

IEEE International Conference on Robotics and Automation (ICRA)

Multi-view perception techniques for transparent object detection and manipulation.

📄 Paper 🌐 Website 💻 Code

AR2D2: Training a Robot Without A Robot

Jiafei Duan, Yi Ru Wang, Mohit Shridhar, Dieter Fox, Ranjay Krishna

Conference on Robot Learning (CoRL)

A novel approach for training robotic systems without requiring physical robot hardware.

📄 Paper 🌐 Website

NEWTON: Are Large Language Models Capable of Physical Reasoning?

Yi Ru Wang, Jiafei Duan, Dieter Fox, Siddhartha Srinivasa

Conference on Empirical Methods in Natural Language Processing (EMNLP)

Investigation of large language models capabilities for physical reasoning tasks.

📄 Paper 🌐 Website 💻 Code

C

CONetV2: Efficient Auto-Channel Size Optimization for CNNs

Yi Ru Wang*, Samir Khaki*, Weihang Zheng*, Mahdi S. Hosseini*, Konstantinos N. Plataniotis

International Conference on Machine Learning and Applications (ICMLA) - Oral Presentation

Efficient auto-channel size optimization techniques for convolutional neural networks.

📄 Paper 💻 Code

S

Seeing Glass: Joint Point-Cloud and Depth Completion for Transparent Objects

Yi Ru Wang*, Haoping Xu*, Sagi Eppel, Alan Aspuru-Guzik, Florian Shkurti, Animesh Garg

5th Annual Conference on Robot Learning (CoRL) - Oral Presentation (6.5% Acceptance Rate)

Joint point-cloud and depth completion techniques for transparent object perception.

📄 Paper 🌐 Website

P

Predicting 3d shapes, masks, and properties of materials, liquids, and objects inside transparent containers, using the Transproteus CGI dataset

Sagi Eppel, Haoping Xu, Yi Ru Wang, Alan Aspuru-Guzik

In Submission

Prediction of 3D shapes, masks, and properties of materials inside transparent containers using the Transproteus CGI dataset.

📄 Paper 💻 Code