Nicklas Hansen

I am a PhD student at UC San Diego, advised by Prof. Xiaolong Wang and Prof. Hao Su. I interned at Meta AI (FAIR) during 2022. Before starting my PhD, I was a visiting student at UC Berkeley and a research intern at Berkeley AI Research, where I was fortunate to work with Prof. Lerrel Pinto, Prof. Xiaolong Wang, and Prof. Alexei Efros.

I received my Bachelor's and Master's degrees from the Technical University of Denmark (DTU), where I worked with Prof. Ole Winther and Prof. Morten Mørup. I have also spent time at Nanyang Technological University (NTUsg) in lovely Singapore, as well as Retune-DSP (acquired by NXP), and raffle.ai.

Research interest

I am broadly interested in research on the generalization and adaptation of neural agents. I believe AI in the future should be flexible, learn with little supervision, and learn continuously over their lifetime. I work with reinforcement learning, robotics, and computer vision.

Publications and preprints

Papers sorted by recency. Representative papers are highlighted.

MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation
Patrick Lancaster, Nicklas Hansen, Aravind Rajeswaran, Vikash Kumar
arXiv, 2023
project page / arXiv / bibtex

GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields
Yanjie Ze*, Ge Yan*, Yueh-Hua Wu*, Annabella Macaluso, Yuying Ge, Jianglong Ye, Nicklas Hansen, Li Erran Li, Xiaolong Wang
Conference on Robot Learning (CoRL), 2023 (Oral)
project page / arXiv / code / bibtex

Finetuning Offline World Models in the Real World
Yunhai Feng*, Nicklas Hansen*, Ziyan Xiong*, Chandramouli Rajagopalan, Xiaolong Wang
Conference on Robot Learning (CoRL), 2023 (Oral)
project page / openreview / bibtex

On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
Nicklas Hansen*, Zhecheng Yuan*, Yanjie Ze*, Tongzhou Mu*, Aravind Rajeswaran+, Hao Su+, Huazhe Xu+, Xiaolong Wang+
International Conference on Machine Learning (ICML), 2023
arXiv / code / bibtex

MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
Nicklas Hansen, Yixin Lin, Hao Su, Xiaolong Wang, Vikash Kumar, Aravind Rajeswaran
International Conference on Learning Representations (ICLR), 2023
project page / arXiv / code / bibtex

On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
Yifan Xu*, Nicklas Hansen*, Zirui Wang, Yung-Chieh Chan, Hao Su, Zhuowen Tu
International Conference on Learning Representations (ICLR), 2023
project page / arXiv / code / bibtex

Visual Reinforcement Learning with Self-Supervised 3D Representations
Yanjie Ze*, Nicklas Hansen*, Yinbo Chen, Mohit Jain, Xiaolong Wang
Robotics and Automation Letters (RA-L), 2023
project page / arXiv / code / bibtex

Graph Inverse Reinforcement Learning from Diverse Videos
Sateesh Kumar, Jonathan Zamora*, Nicklas Hansen*, Rishabh Jangir, Xiaolong Wang
Conference on Robot Learning (CoRL), 2022 (Oral)
project page / arXiv / bibtex

Temporal Difference Learning for Model Predictive Control
Nicklas Hansen, Xiaolong Wang*, Hao Su*
International Conference on Machine Learning (ICML), 2022
project page / arXiv / slides / code / bibtex

Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation
Rishabh Jangir*, Nicklas Hansen*, Sambaran Ghosal, Mohit Jain, Xiaolong Wang
Robotics and Automation Letters (RA-L), 2022
International Conference on Robotics and Automation (ICRA), 2022
project page / arXiv / code / bibtex

Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
Nicklas Hansen, Hao Su, Xiaolong Wang
Conference on Neural Information Processing Systems (NeurIPS), 2021
project page / arXiv / code / bibtex

Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
Ruihan Yang*, Minghao Zhang*, Nicklas Hansen, Huazhe Xu, Xiaolong Wang
International Conference on Learning Representations (ICLR), 2022 (Spotlight)
project page / arXiv / bibtex

Generalization in Reinforcement Learning by Soft Data Augmentation
Nicklas Hansen, Xiaolong Wang
International Conference on Robotics and Automation (ICRA), 2021
project page / arXiv / code / bibtex

Self-Supervised Policy Adaptation during Deployment
Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Alenyà, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang
International Conference on Learning Representations (ICLR), 2021 (Spotlight)
project page / arXiv / blog / code / bibtex

Generalization in Visual Reinforcement Learning
Nicklas Hansen
Master Thesis, 2021
pdf / bibtex

Short Term Blood Glucose Prediction based on Continuous Glucose Monitoring Data
Ali Mohebbi, Alexander R. Johansen, Nicklas Hansen, Peter E. Christensen, Jens M. Tarp, Morten L. Jensen, Henrik Bengtsson, Morten Mørup
Engineering in Medicine and Biology Conference (EMBC), 2020
arXiv / bibtex

Misc. open-source projects

TD-MPC Official Implementation⭐ 218
Nicklas Hansen, Xiaolong Wang*, Hao Su*
Mar 2022
project page / arXiv / slides / code / bibtex

DMControl Generalization Benchmark⭐ 129
Nicklas Hansen, Xiaolong Wang
Nov 2020
project page / arXiv / code / bibtex

How to build RNNs and LSTMs from scratch with NumPy⭐ 212
Nicklas Hansen, Peter E. Christensen, Alexander R. Johansen
Oct 2019
colab / code

Voice Activity Detection in Noisy Environments⭐ 173
Nicklas Hansen*, Simon H. Albrechtsen*
Dec 2018
tech report / code / bibtex

Press coverage

I have been mentioned in various media in connection with my research. Here's a few selected articles:

Contact

You are very welcome to contact me regarding my research. I typically respond within a few days.
I can be contacted directly at hello [at] nicklashansen 。com