Our group conducts fundamental research towards collaborative artificial intelligence (CAI) at the intersection of multimodal machine learning, computational cognitive modelling, computer vision, and human-machine interaction.
Humboldt Research Fellows
We invite applications from excellent PhD graduates who are interested in doing a PostDoc in our group. We are eligible to host excellent postdoctoral researchers for up to 2 years through a prestigious Humboldt Research Fellowship. If you are interested in applying for such a fellowship with our support, you can find more details here.
PhD / PostDoc Position Available
We have a PhD / PostDoc position available in the context of a DFG grant. The topic is "Long-term and Few-shot Action Anticipation using Causal Representation Learning".
Project Description: The goal of this project is to develop computational methods for causal representation learning for long-term and few-shot action anticipation. Action anticipation and proactive adaptation are key for efficient human-AI collaboration. We will specifically study settings in which an AI system parses video recordings of humans to learn structural causal models of their behaviour.
If you are highly motivated and capable of addressing and solving scientifically challenging problems, and if you are interested in doing research in an internationally oriented and highly successful team, you should apply! Please submit your complete application as detailed below.
Latest News
Spotlight
- NeurIPS'26High Entropy Regularization Leads to Symmetry Equivariant Policies in Dec-POMDPs
- TVCG'26HAGI++: Head-Assisted Gaze Imputation and Generation
- RLC'26The Yōkai Learning Environment: Tracking Beliefs Over Space and Time
- ACL'26ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback
- ICML'26Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
- ICML'26MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
- ICLR'26RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
- PETS'26Gaze3P: Gaze-Based Prediction of User-Perceived Privacy
- TMLR'25The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design
- IMWUT'25Through the Eyes of Emotion: A Multi-faceted Eye Tracking Dataset for Emotion Recognition in Virtual Reality
- UIST'25HAGI: Head-Assisted Gaze Imputation for Mobile Eye Trackers
- TVCG'25HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality
- EMNLP'25ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions
- SIGGRAPH'25HOIGaze: Gaze Estimation During Hand-Object Interactions in Extended Reality Exploiting Eye-Hand-Head Coordination
- CVPR'25V2Dial: Unification of Video and Visual Dialog via Multimodal Experts
- CHI'25Chartist: Task-driven Eye Movement Control for Chart Reading
- CHI'25SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation
- UIST'24DisMouse: Disentangling Information from Mouse Movement Data
- ECCV'24Multi-Modal Video Dialog State Tracking in the Wild
- IROS'24GazeMotion: Gaze-guided Human Motion Forecasting
- ACL'24Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition
- TVCG'24Pose2Gaze: Eye-body Coordination during Daily Activities for Gaze Prediction from Full-body Poses
- TVCG'24HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes
- CHI'24SalChartQA: Question-driven Saliency on Information Visualisations
- CHI'24Mouse2Vec: Learning Reusable Semantic Representations of Mouse Behaviour
- AAAI'24Neural Reasoning About Agents’ Goals, Preferences, and Actions
- PACM HCI'24Mindful Explanations: Prevalence and Impact of Mind Attribution in XAI Research
- TVCG'23Scanpath Prediction on Information Visualisations
- CHI'23Impact of Privacy Protection Methods of Lifelogs on Remembered Memories
- UIST'23SUPREYES: SUPer Resolution for EYES Using Implicit Neural Representation Learning
- UIST'23Usable and Fast Interactive Mental Face Reconstruction
- TOCHI'22Understanding, Addressing, and Analysing Digital Eye Strain in Virtual Reality Head-Mounted Displays
- TVCG'22VisRecall: Quantifying Information Visualisation Recallability via Question Answering
- CHI'22Designing for Noticeability: The Impact of Visual Importance on Desktop Notifications










