Max Argus

argus.max at gmail.com

I'm currently a Research Scientist at the Allen Institute for AI (Ai2), where I work with Dieter Fox on the robotics team. I am also a postdoc at the University of Washington with Ranjay Krishna.

I work on scaling simulation for robot learning and evaluation. Previously I have worked on learning from demonstrations and diverse machine learning and computer vision problems.

Before that I was a postdoc at the University of Freiburg, working with Abhinav Valada. My PhD was supervised by Thomas Brox and Wolfram Burgard. I hold a B.Sc. and M.Sc. in Physics from the University of Heidelberg (Björn Ommer), and interned at BAIR (Evan Shelhamer) and Symbio Robotics.

CV / GitHub / Google Scholar / LinkedIn / Freiburg page
Max Argus

News

Oct 2026Talk at Yale with Aron Dollar.
Sep 2026Talk at General Robotics.
Jul 2026Talk at the German Aerospace Center (DLR), hosted by Rudolph Triebel.
2026🏆 MolmoBot accepted as an oral at CoRL 2026 (top 10.5% of accepted papers).
2026🏆 MolmoMotion accepted as a spotlight at NeurIPS 2026 (top 3.7% of accepted papers).
Aug 2024Ditto published at IROS. Project page.
Aug 2024Our work on climate adaptation was featured in Badische Zeitung. Article.
Mar 2024Talk at EPFL with Aude Billard.
Mar 2023Talk at KTH with Danica Kragic.

Research

Highlighted / All

FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences
O Rayyan, Z Li, M Argus, Y Jiang, C Yu, C Jiang, Y Cui
arXiv:2608.17027, Aug 2026
arXiv
MolmoSpaces-CommonSense: Evaluating Commonsense in Robotic Manipulation Policies
A Guru, M Argus, JS Park, J Duan, A Farhadi, R Krishna
3rd Workshop on Semantic Reasoning and Goal Understanding in Robotics (RSS 2026), 2026
paper
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
A Deshpande, M Guru, R Hendrix, S Jauhri, A Eftekhar, R Tripathi, … M Argus, …
🏆 CoRL 2026 (Oral), Mar 2026
arXiv / project
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
J Zhang, C Zheng, Y Yang, M Argus, R Soraki, W Han, T Anderson, C Li, S Liu, J Duan, Z Ren, J Zhang, R Krishna
🏆 NeurIPS 2026 (Spotlight), Jun 2026
arXiv / blog
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
Y Kim, W Pumacay, O Rayyan, M Argus, W Han, E VanderBilt, J Salvador, …
arXiv:2602.11337, Feb 2026
arXiv / code
cVLA: Towards Efficient Camera-Space VLAs
M Argus, J Bratulic, H Masnavi, M Velikanov, N Heppert, A Valada, T Brox
arXiv:2507.02190, Jul 2025
arXiv
When and How Does CLIP Enable Domain and Compositional Generalization?
E Kempf, S Schrodi, M Argus, T Brox
arXiv:2502.09507, 2025
arXiv
Two effects, one trigger: On the modality gap, object bias, and information imbalance in contrastive vision-language models
S Schrodi, DT Hoffmann, M Argus, V Fischer, T Brox
ICLR, 2025
arXiv
Ditto: Demonstration imitation by trajectory transformation
N Heppert, M Argus, T Welschehold, T Brox, A Valada
IROS, 2024
project
CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
A Bhatt, D Palenicek, B Belousov, M Argus, A Amiranashvili, T Brox, …
ICLR, 2024
paper / code
Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching
E Chisari, N Heppert, M Argus, T Welschehold, T Brox, A Valada
CoRL, 2024 (project)
arXiv / project
Concept Bottleneck Models Without Predefined Concepts
S Schrodi, J Schur, M Argus, T Brox
arXiv:2407.03921, 2024
arXiv
Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection
S Galesso, M Argus, T Brox
ICCV Workshops (UnCV), 2023
paper
Latent Diffusion Counterfactual Explanations
K Farid, S Schrodi, M Argus, T Brox
arXiv:2310.06668, 2023
arXiv
Contrastive representation learning for hand shape estimation
C Zimmermann, M Argus, T Brox
DAGM GCPR, 2021
arXiv / project
Temporal shift GAN for large scale video generation
A Munoz, M Zolfaghari, M Argus, T Brox
WACV, 2021
arXiv
Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
L Hermann, M Argus, A Eitel, A Amiranashvili, W Burgard, T Brox
ICRA, 2020
arXiv / project
FlowControl: Optical Flow Based Visual Servoing
M Argus, L Hermann, J Long, T Brox
IROS, 2020
arXiv / project
FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
C Zimmermann, D Ceylan, J Yang, B Russell, M Argus, T Brox
ICCV, 2019
arXiv / project
CrossNorm: Normalization for off-policy TD reinforcement learning
A Bhatt, M Argus, A Amiranashvili, T Brox
arXiv:1902.05605, 2019
arXiv
Loss is its own reward: Self-supervision for reinforcement learning
E Shelhamer, P Mahmoudieh, M Argus, T Darrell
arXiv:1612.07307, 2016
arXiv
Power grasp planning for anthropomorphic robot hands
MA Roa, MJ Argus, D Leidner, C Borst, G Hirzinger
ICRA, 2012
paper

Invited Talks

Oct 2026Yale University, hosted by Aron Dollar
“Scaling Robot Learning and Evaluation in Simulation”
Sep 2026General Robotics
“Scaling Robot Learning and Evaluation in Simulation”
Jul 2026German Aerospace Center (DLR), hosted by Rudolph Triebel
“Beyond Behavior-Cloning from Teleoperation for Robot Models”
Mar 2024EPFL, hosted by Aude Billard
“Learning Manipulation from Human Demonstrations”
Mar 2023KTH, hosted by Danica Kragic
“Learning Manipulation from Human Demonstrations”

Mt. Fuji