9 papers
Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning
Sara Rajaram, R. James Cotton, Fabian H. Sinz
The paper proposes SARA, a contrastive method that learns latent representations of preferred behaviors and uses similarity as a reward signal, improving robustness to noisy human…
OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens
Konstantin F. Willeke, Polina Turishcheva, Alex Gilbert +18
Scaling data and artificial neural networks has transformed AI, driving breakthroughs in language and vision. Whether similar principles apply to modeling brain activity remains un…
Calibrated Uncertainty for Trustworthy Clinical Gait Analysis Using Probabilistic Multiview Markerless Motion Capture
Seth Donahue, Irina Djuraskovic, Kunal Shah +3
Video-based human movement analysis holds potential for movement assessment in clinical practice and research. However, the clinical implementation and trust of multi-view markerle…
Monte Carlo Event Generation with Continuous Normalizing Flows
Enrico Bothmann, Timo JanÃen, Max Knobbe +2
We apply Continuous Normalizing Flows trained with the Flow Matching method to the problem of phase-space sampling in Monte Carlo event generation for high-energy collider physics.…
Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors
Finn Schmidt, Polina Turishcheva, Suhas Shrinivasan +1
The neural activity in the visual processing is influenced by both external stimuli and internal brain states. Ideally, a neural predictive model should account for both of them. C…
TRACE: Contrastive learning for multi-trial time-series data in neuroscience
Lisa Schmors, Dominic Gonschorek, Jan Niklas Böhm +9
Modern neural recording techniques such as two-photon imaging or Neuropixel probes allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Co…