Yunsheng Tian

Yunsheng Tian

Member of Technical Staff @ Amazon FAR

Yunsheng Tian

Member of Technical Staff @ Amazon FAR

I am a Member of Technical Staff at Amazon Frontier AI & Robotics, where I build and deploy human-level robotic foundation models and lead a team pushing the frontier of open-world navigation.

I earned my PhD at MIT CSAIL, where I built a general robotic assembly system for diverse objects, with innovations in task and motion planning, reinforcement learning, and physics simulation.

Outside research, I am a picky foodie spoiled by my wife, who knows how to cook everything.

Research

Scalable Assembly of General Objects

Scalable Assembly of General Objects 🎓

PhD Thesis
A scalable system towards fully automated and flexible robotic assembly that generalizes over diverse geometries.
PDF
NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception

NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception 🤖

RSS 2026 (Best System Paper Award)
A neural actuator model for low-cost servo-driven robot platforms.
PDF Code Project Poster
Fabrica: Dual-Arm Assembly of General Multi-Part Objects via Integrated Planning and Learning

Fabrica: Dual-Arm Assembly of General Multi-Part Objects via Integrated Planning and Learning 🤖

CoRL 2025 (Best Paper Award)
Generalizable, long-horizon, and contact-rich multi-part object assembly by dual-arm robots in the real world.
PDF Code Project Video Talk
A multimodal robotic platform for multi-element electrocatalyst discovery

A multimodal robotic platform for multi-element electrocatalyst discovery 🧠 🤖

Zhen Zhang, Zhichu Ren, Chia-Wei Hsu, Weibin Chen, Zhang-Wei Hong, Chi-Feng Lee, Aubrey Penn, Hongbin Xu, Daniel J. Zheng, Shuhan Miao, Yimeng Huang, Yifan Gao, Weiyin Chen, Hugh Smith, Yaoshen Niu, Yunsheng Tian, Ying-Rui Lu, Yu-Cheng Shao, Sipei Li, Hsiao-Tsu Wang, Iwnetim I. Abate, Pulkit Agrawal, Yang Shao-Horn, Ju Li
Nature 2025
NeurIPS 2023 RealML Workshop (Best Student Paper Award)
Accelerated scientific discovery through large multimodal models, Bayesian optimization, and autonomous robots.
PDF Code Video
ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility

ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility 🤖 🧠

ICRA 2024
MIT MIMO Symposium 2023 (Zetta Prize, Best Application of AI in Industry)
Automated robotic assembly plan generation for complex and general-shaped assemblies.
PDF Code Dataset Project Poster Slides Video
Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints

Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints 🧠

ICML 2024
Efficient global optimizer for physical designs with unknown constraints.
PDF Code Poster
Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly

Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly 🤖 🎨

ACM TOG / SIGGRAPH Asia 2022 (Journal Track)
Physics makes motion planning for complex assemblies simple, fast, and generalizable.
PDF Code Dataset Project Video Talk MIT News
JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints

JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints 🧠 🎨

CVPR 2022
Learning to assemble on a big CAD assembly dataset approaching human-level accuracy.
PDF Code Dataset
Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots

Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots 🤖

NeurIPS 2021
The first and largest benchmark for evolving soft robot morphology.
PDF Code Project Poster Video MIT News Wired IEEE Spectrum
Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations

Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations 🧠

NeurIPS 2020
Efficient multi-objective optimizer for expensive black-box functions.
PDF Code Poster Video Supplementary
Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control

Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control 🧠 🤖

ICML 2020
Efficient multi-objective RL for discovering all Pareto-optimal policies.
PDF Code Project Video Talk Supplementary
Fluid Directed Rigid Body Control using Deep Reinforcement Learning

Fluid Directed Rigid Body Control using Deep Reinforcement Learning 🤖 🎨

Yunsheng Tian, Pingchuan Ma, Zherong Pan, Bo Ren, Dinesh Manocha (* indicates equal contribution)
ACM TOG / SIGGRAPH 2018
Deep RL can control high-dimensional fluid-rigid coupling dynamics.
PDF Project Video DOI Talk