Accepted

MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs
Decoding visual stimuli from neural population activity is crucial for understanding the brain and for applications in brain-machine …
Jan Sobotka, Luca Baroni, Ján Antolík
Poster OpenReview
Weak-to-Strong Generalization under Distribution Shifts
As future superhuman models become increasingly complex, accurately supervising their behavior may exceed human capabilities. Recent …
Myeongho Jeon, Jan Sobotka, Suhwan Choi, Maria Brbic
Poster OpenReview
Reverse-Engineering Memory in DreamerV3: From Sparse Representations to Functional Circuits
Understanding how reinforcement learning (RL) agents with recurrent neural network architectures encode and use memory remains an open …
Jan Sobotka, Auke Ijspeert, Guillaume Bellegarda
OpenReview