Skip to main content

Publications

Our research contributions spanning computational neuroscience, artificial intelligence, and computer vision. For a complete list, visit our Google Scholar page.

Year:
Type:

2026

Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale

C Li*, C Wang*, B Ziliotto, M Simos, J Kovecses, G Durandau, A Mathis

Preprint
embodied AI
reinforcement learning
biomechanics

LLaVAction: evaluating and training multi-modal large language models for action recognition

S Ye*, H Qi*, A Mathis**, MW Mathis**

ICLR 2026
action recognition
multimodal learning
LLMs

Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor control

M Simos, AS Chiappa, A Mathis

ICRA 2026
reinforcement learning
motor control
biomechanics

The behavior biopsy: Interpreting animal behavior as embodied, situated, and hierarchical

A Bonnetto*, S Mamooler*, C Li*, A Mathis

Current Opinion in Neurobiology
behavior analysis
computational ethology
neuroscience

MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence

C Wang, ..., C Li, M Simos, B Ziliotto, A Mathis, ..., V Caggiano

arXiv preprint arXiv:2605.15650
embodied AI
motor control
biomechanics

AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding

H Qi, K Qu, M Rad, R Wang, A Mathis, M Pollefeys

arXiv preprint arXiv:2603.28696
video understanding
multimodal learning
LLMs

Closed-loop imitation learning reveals muscle-centric and latent-goal codes in primate sensorimotor cortex

AM Vargas, AP Rotondo, AS Chiappa, MW Mathis, A Mathis

bioRxiv
imitation learning
motor control
neuroscience

Individual identification of brown bears using pose-aware metric learning

B Rosenberg, M Zhou, N Wolf, MW Mathis, BP Harris, A Mathis

Current Biology
wildlife conservation
pose estimation
metric learning

2025

Arnold: a generalist muscle transformer policy

AS Chiappa, B An, M Simos, C Li, A Mathis

arXiv preprint
sensorimotor control
robotics
reinforcement learning

DLC2Action: A Deep Learning-based Toolbox for Automated Behavior Segmentation

E Kozlova, A Bonnetto, A Mathis

bioRxiv preprint
behavior analysis
deep learning
neuroscience

EPFL-Smart-Kitchen: An Ego-Exo Multi-Modal Dataset for Challenging Action and Motion Understanding in Video-Language Models

A Bonnetto*, H Qi*, F Leong, M Tashkovska, M Rad, S Shokur, F Hummel, S Micera, M Pollefeys, A Mathis

NeurIPS 2025 Datasets and Benchmarks Track
datasets
3D kinematics
multimodal learning

MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps

V Gabeff, H Qi, B Flaherty, G Sumbül, A Mathis*, D Tuia*

CVPR (highlight)
wildlife conservation
datasets
computer vision

Imitation learning of dexterous hand control uncovers muscle-level representations in primate sensorimotor cortex

AM Vargas, AP Rotondo, AS Chiappa, MW Mathis, A Mathis

Foundation Models for the Brain and Body Workshop - NeurIPS
imitation learning
motor control
neuroscience

Deep‐learning models of the ascending proprioceptive pathway are subject to illusions

A Perez Rotondo, M Simos, F David, S Pigeon, O Blanke, A Mathis

Experimental Physiology
proprioception
neural networks
sensorimotor control

Climbing out of the lab: studying motor planning and coarticulation in the climbing gym

A Bonnetto, A Mathis

Journal of Neurophysiology
motor control
behavior analysis
neuroscience

Fine-tuning Vision-Language Models for Animal Behavior Analysis

S Mamooler, H Qi, V Gabeff, S Montariol, A Bosselut, A Mathis

LLM for Scientific Discovery: Reasoning
animal behavior
vision-language models
multimodal learning

PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detection

S Mamooler, S Montariol, A Mathis, A Bosselut

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
NLP
in-context learning
named entity recognition

2024

Acquiring musculoskeletal skills with curriculum-based reinforcement learning

AS Chiappa, P Tano, N Patel, A Ingster, A Pouget, A Mathis

Neuron
reinforcement learning
motor control
curriculum learning

Decoding the brain: From neural representations to mechanistic models

MW Mathis, AP Rotondo, EF Chang, AS Tolias, A Mathis

CellVol. 187 (21)pp. 5814-5832
neuroscience
neural decoding
mechanistic models

Elucidating the Hierarchical Nature of Behavior with Masked Autoencoders

L Stoffl, A Bonnetto, S d'Ascoli, A Mathis

European Conference on Computer Vision
behavior analysis
self-supervised learning
ECCV

Task-driven neural network models predict neural dynamics of proprioception

A Marin Vargas*, A Bisi*, AS Chiappa, C Versteeg, LE Miller, A Mathis

Cell
proprioception
neural networks
sensorimotor control

SuperAnimal models pretrained for plug-and-play analysis of animal behavior

S Ye, A Filippova, J Lauer, M Vidal, St Schneider, T Qiu, A Mathis, MW Mathis

Nature Communications
pose estimation
transfer learning
animal behavior

WildCLIP: Scene and animal attribute retrieval from camera trap data with domain-adapted vision-language models

V Gabeff, M Russwurm, D Tuia, A Mathis

International Journal of Computer Vision (in press)
wildlife conservation
vision-language models
CLIP

Could ChatGPT get an engineering degree? Evaluating higher education vulnerability to AI assistants

Beatriz Borges, Negar Foroutan, Deniz Bayazit, Anna Sotnikova, Syrielle Montariol, Tanya Nazaretsky, Mohammadreza Banaei, Alireza Sakhaeirad, Philippe Servant, Seyed Parsa Neshaei, Jibril Frej, Angelika Romanou, Gail Weiss, Sepideh Mamooler, Zeming Chen, Simin Fan, Silin Gao, Mete Ismayilzada, Debjit Paul, Philippe Schwaller, Sacha Friedli, Patrick Jermann, Tanja Käser, Antoine Bosselut, EPFL Grader Consortium, EPFL Data Consortium

Proceedings of the National Academy of Sciences
AI assistants
education
assessment

MyoChallenge 2023: Towards human-level dexterity and agility

Vittorio Caggiano, Guillaume Durandau, Huiyi Wang, Chun Kwang Tan, Pierre Schumacher, Huawei Wang, Alberto Silvio Chiappa, Alessandro Marin Vargas, Alexander Mathis, Jungdam Won, Jungnam Park, Gunwoo Park, Beomsoo Shin, Minseung Kim, Seungbum Koo, Zhuo Yang, Wei Dang, Heng Cai, Jianfei Song, Seungmoon Song, Massimo Sartori, Vikash Kumar

NeurIPS 2024 Datasets and Benchmarks Track
embodied AI
motor control
biomechanics

HOISDF: Constraining 3D hand-object pose estimation with global signed distance fields

H Qi, C Zhao, M Salzmann, A Mathis

CVPR 2024
3D pose estimation
hand-object interaction
computer vision

Modeling Sensorimotor Processing with Physics-Informed Neural Networks

A Perez Rotondo, A Marin Vargas, M Dimitriou, A Mathis

bioRxiv
proprioception
physics-informed learning
sensorimotor control

2023

Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity

M Zhou*, L Stoffl*, MW Mathis, A Mathis

ICCV
pose estimation
crowded scenes
computer vision

AmadeusGPT: a natural language interface for interactive animal behavioral analysis

S Ye, J Lauer, M Zhou, A Mathis, MW Mathis

NeurIPS
NLP
behavior analysis
GPT

Contrasting action and posture coding with hierarchical deep neural network models of proprioception

Kai J. Sandbrink*, Pranav Mamidanna*, Claudio Michaelis, Matthias Bethge*, Mackenzie W. Mathis*, Alexander Mathis*

eLife
proprioception
neural networks
sensorimotor control

MyoChallenge 2022: Learning contact-rich manipulation using a musculoskeletal hand

Vittorio Caggiano, ..., Alberto Chiappa, Alexander Mathis, ..., Vikash Kumar

Proceedings of the NeurIPS 2022 Competitions Track
embodied AI
motor control
biomechanics

Latent exploration for reinforcement learning

AS Chiappa, A Marin Vargas, A Huang, A Mathis

NeurIPS 2023
reinforcement learning
exploration
motor control

2022

DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body

Alberto Silvio Chiappa, Alessandro Marin Vargas, Alexander Mathis

NeurIPS
reinforcement learning
locomotion
morphology

Multi-animal pose estimation, identification and tracking with DeepLabCut

Jessy Lauer, Mu Zhou, Shaokai Ye, et al., Mackenzie W Mathis*, Alexander Mathis*

Nature Neuroscience
pose estimation
tracking
DeepLabCut

2021

Seeing biodiversity: perspectives in artificial intelligence for wildlife conservation

Devis Tuia, Benjamin Kellenberger, Sara Beery, et al., Alexander Mathis, Mackenzie W Mathis, et al.

Nature Communications
wildlife conservation
artificial intelligence
computer vision

Out-of-distribution generalization of internal models is correlated with reward

MWM Khushdeep S.* Mann, Steffen* Schneider, Alberto Chiappa, Jin H. Lee ...

SSL-RL Workshop at ICLR

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

L Stoffl, M Vidal, A Mathis

arXiv preprint arXiv:2103.12115

Measuring and modeling the motor system with machine learning

SB Hausmann, AM Vargas, A Mathis, MW Mathis

Current Opinion in Neurobiology

2020

A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives

Alexander Mathis, Steffen Schneider, Jessy Lauer, Mackenzie W. Mathis

NeuronVol. 108pp. P44-65
deep learning
motion capture
pose estimation

2019

Using DeepLabCut for 3D markerless pose estimation across species and behaviors

Tanmay Nath*, Alexander Mathis*, An Chi Chen, Amir Patel, Matthias Bethge, Mackenzie W. Mathis

Nature ProtocolsVol. 14pp. 2152-2176
pose estimation
DeepLabCut
3D tracking

2018

DeepLabCut: Markerless tracking of user-defined features with deep learning

Alexander Mathis, Pranav Mamidanna, Kevin M. Cury, Taiga Abe, Venkatesh N. Murthy, Mackenzie W. Mathis*, Matthias Bethge*

Nature NeuroscienceVol. 21pp. 1281-1289
pose estimation
DeepLabCut
markerless tracking