My name is Ben Eisner, and I’m a Machine Learning and Robotics researcher. I build robotic systems that learn to interact with the unstructured world.
I’m currently a 5th-Year Ph.D. student in the Robotics Institute at Carnegie Mellon University. I’m a member of the Robots Perceiving and Doing Lab, led by Prof. David Held. Right now, I’m working on some techniques for policy transfer. My research is supported in part by the NSF Graduate Research Fellowship.
Here is a recent version of my academic cv, my Google Scholar profile, and my Github profile.
You can reach me at ben.a.eisner@gmail.com.
9/4/24: Two of our papers were accepted to CoRL 2024! One on manipulating articulated objects under uncertainty, and another on relative placement for non-rigid objects.
1/16/24: Our paper on provably-SE(3)-equivariant geometric reasoning from vision has been accepted to ICLR 2024! This work incorporates work conducted during my internship at DeepMind in 2022.
8/30/23: Our paper on manipulating articulated objects has been accepted to CoRL 2023!
9/10/22: Our paper on learning dense, optimization-based pose estimation for robotics tasks, was accepted to CoRL 2022!
6/20/22: Our paper on learning 3D flow for articulation manipulation was nominated for Best Paper at RSS 2022!
3/30/20: I was selected to receive the NSF Graduate Research Fellowship for the fellowship class of 2020!
FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation
Yishu Li, Wen Hui Leng, Yiming Fang, Ben Eisner, David Held
CoRL 2024
website | OpenReview
Non-rigid Relative Placement through 3D Dense Diffusion
Eric Cai, Octavian Donca, Ben Eisner, David Held
CoRL 2024
website | OpenReview
Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
Ben Eisner, Yi Yang, Todor Davchev, Mel Vecerik, Jonathan Scholz, David Held
ICLR 2024
website | [arXiv] (https://arxiv.org/abs/2404.13478) | OpenReview
FlowBot++: Learning Generalized Articulated Objects Manipulation via Articulation Projection
Harry Zhang, Ben Eisner, David Held
CoRL 2023
website | arXiv
On Time-Indexing as Inductive Bias in Deep RL for Sequential Manipulation Tasks
M. Nomaan Qureshi, Ben Eisner, David Held
Learning Meets Model-based Methods for Manipulation and Grasping Workshop @ IROS 2023
arXiv
TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation
Chuer Pan*, Brian Okorn*, Harry Zhang*, Ben Eisner*, David Held
CoRL 2022
website | OpenReview
FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects
Ben Eisner*, Harry Zhang*, David Held
RSS 2022, Best Paper Finalist
website | arXiv
Deep Sequenced Linear Dynamical Systems for Manipulation Policy Learning
M. Nomaan Qureshi, Ben Eisner, David Held
ICLR 2022 Workshop on Generalizable Policy Learning in Physical World
website
Self-supervised Transparent Liquid Segmentation for Robotic Pouring
Gautham Narasimhan, Kai Zhang, Ben Eisner, Xingyu Lin, David Held
ICRA 2022
website | arXiv
Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction
Daniel Yang, Tarik Tosun, Ben Eisner, Volkan Isler, Daniel Lee
ICRA 2021
arxiv
Reward Prediction Error as an Exploration Objective in Deep RL
Riley Simmons-Edler, Ben Eisner, Daniel Yang, Anthony Bisulco, Eric Mitchell, Sebastian Seung, Daniel Lee
IJCAI 2020 (Earlier draft presented at NeurIPS 2020 Workshop on Deep RL)
arxiv
Pixels to Plans: Learning Non-Prehensile Manipulation by Imitating a Planner
Tarik Tosun*, Eric Mitchell*, Ben Eisner, Jinwook Huh, Bhoram Lee, Daewon Lee, Volkan Isler, Sebastian Seung, Daniel Lee
IROS 2019
arxiv | website | video
Q-Learning for Continuous Actions with Cross-Entropy Guided Policies
Riley Simmons-Edler*, Ben Eisner*, Eric Mitchell, Sebastian Seung, Daniel Lee
ICML 2019 Workshop on RL4RealLife
arxiv
Deep Learning Methods for 3D Segmentation of Neural Tissue in EM Images
Ben Eisner
Princeton University Senior Thesis
thesis | project
emoji2vec: Learning emoji representations from their description
Ben Eisner, Tim Rocktäschel, Isabelle Augenstein, Matko Bošnjak, Sebastian Riedel
Best Paper at EMNLP 2016 Workshop on SocialNLP
arxiv | project