5 papers
Spectral Alignment in Forward-Backward Representations via Temporal Abstraction
Seyed Mahdi B. Azad, Jasper Hoffmann, Iman Nematollahi +3
Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enforcing a low-rank factorization. Howeve…
BLINK: Behavioral Latent Modeling of NK Cell Cytotoxicity
Iman Nematollahi, Jose Francisco Villena-Ossa, Alina Moter +6
Machine learning models of cellular interaction dynamics hold promise for understanding cell behavior. Natural killer (NK) cell cytotoxicity is a prominent example of such interact…
DiWA: Diffusion Policy Adaptation with World Models
Akshay L Chandra, Iman Nematollahi, Chenguang Huang +3
Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward pro…
LUMOS: Language-Conditioned Imitation Learning with World Models
Iman Nematollahi, Branton DeMoss, Akshay L Chandra +3
We introduce LUMOS, a language-conditioned multi-task imitation learning framework for robotics. LUMOS learns skills by practicing them over many long-horizon rollouts in the laten…
Bayesian Optimization for Sample-Efficient Policy Improvement in Robotic Manipulation
Adrian Röfer, Iman Nematollahi, Tim Welschehold +2
Sample efficient learning of manipulation skills poses a major challenge in robotics. While recent approaches demonstrate impressive advances in the type of task that can be addres…