News
- [May 2025]
Research featured on Bloomberg News - "The Rise of AI in Factories"
- [Mar 2025]
Invited talk at Google DeepMind - "Inference-Time
Policy Steering"
- [Feb 2025]
I defended my PhD thesis! - "Steering Robots with Inference-Time Interactions"
- [Dec 2024]
Invited talk at MIT EI Seminar - "Inference-Time Policy Customization through Interactive Task Specification"
- [Jul 2024]
Organized GenAI-HRI workshop at RSS 2024.
- [Mar 2024]
Invited talk at Brown University Robotics Seminar - "Interactive Task and Motion Imitation"
- [Oct 2023]
Temporal logic imitation was awarded the Best Student Paper at IROS 2023 Workshop.
- [Jan 2023]
PBS News coverage of our human robot interaction exhibition at MIT museum.
Research
Imagine driving with Google Maps, where multiple routes unfold before you. As you take turns and change plans, it adapts instantly recalculating to match your shifting preferences. My research goal is to bring this level of interactivity to multimodal embodied AI, empowering humans to steer pre-trained foundation models at inference-time. For video explainers, check out my MIT Student Spotlight (more technical) or Bloomberg News (more accessible).
|
|
Inference-Time Policy Steering through Human Interactions
Yanwei Wang,
Lirui Wang,
Yilun Du,
Balakumar Sundaralingam,
Xuning Yang,
Yu-Wei Chao,
Claudia Perez-D'Arpino,
Dieter Fox,
Julie Shah
arxiv /
code /
project page /
twitter /
MIT News
ICRA 2025
We propose Inference-Time Policy Steering (ITPS), a framework that leverages human interactions to zero-shot adapt
pre-trained generative policies for downstream tasks without any additional data collection or fine-tuning.
|
|
Versatile Demonstration Interface: Toward More
Flexible Robot Demonstration Collection
Michael Hagenow,
Dimosthenis Kontogiorgos,
Yanwei Wang,
Julie Shah
arxiv
IROS 2025
We present the Versatile Demonstration Interface (VDI), a collaborative robot tool designed to enable seamless
transitions between data collection modes—teleoperation, kinesthetic teaching, and natural demonstrations—without the
need for additional environmental instrumentation.
|
|
Grounding Language Plans in Demonstrations through Counter-factual Perturbations
Yanwei Wang,
Tsun-Hsuan Wang,
Jiayuan Mao,
Michael Hagenow,
Julie Shah
arxiv /
code /
project page /
MIT News /
techcrunch
ICLR 2024 (Spotlight)
This work learns grounding classifiers for LLM planning. Our end-to-end explanation-based network is
trained to differentiate successful demonstrations from failing counterfactuals and as a by-product learns classifiers that ground continuous states
into discrete manipulation mode families without dense labeling.
|
|
Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
Yanwei Wang,
Nadia Figueroa, Shen Li, Ankit Shah, Julie Shah
arxiv
/
code
/
project page
/
PBS News
CoRL 2022 (Oral)
IROS 2023 Workshop ( Best Student Paper, Learning Meets Model-based Methods for Manipulation and Grasping)
We present a continuous motion imitation method that can provably satisfy any discrete plan specified by a Linear Temporal Logic (LTL) formula. Consequently, the imitator is robust to both task- and motion-level disturbances and guaranteed to achieve task success.
|
|
Improving Small Language Models on PubMedQA via Generative Data Augmentation
Zhen Guo,
Yanwei Wang,
Peiqi Wang,
Shangdi Yu
arxiv
KDD 2023 (Foundations and Applications in Large-scale
AI Models Pre-training, Fine-tuning, and Prompt-based Learning Workshop)
We prompt large language models to augment a domain-specific dataset to train specialized small language models that outperform the general-purpose LLM.
|
|
Visual Pre-training for Navigation: What Can We Learn from Noise?
Yanwei Wang,
Ching-Yun Ko,
Pulkit Agrawal
arxiv
/
code
/
project page
IROS 2023
NeurIPS 2022 Workshop (Synthetic Data for Empowering ML Research / Self-Supervised Learning)
By learning how to pan, tilt and zoom its camera to focus on random crops of a noise image, an embodied agent can pick up navigation skills in realistically simulated environments.
|
|
MIT Museum Interactive Robot Exhibition: Teach a Robot Motions
Nadia Figueroa,
Yanwei Wang,
Julie Shah
We installed an interactive exhibition at MIT Museum that allows non-robot-experts to teach a robot an inspection task using demonstrations. The robustness and compliance of the learned motion policy enables visitors (including kids) to physically perturb the system safely 24/7 without losing a success gaurantee.
|
|