← Search

Babak Rahmani

2 accepted papers

2025

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity

ICML 2025spotlight

State-space models (SSMs) and transformers dominate the language modeling landscape. However, they are constrained to a lower computational complexity than classical recurrent neural networks (RNNs), limiting their expressivity. In contrast, RNNs lack parallelization during training, raising fundame…

2022

Natural image synthesis for the retina with variational information bottleneck representation

NeurIPS 2022accept

In the early visual system, high dimensional natural stimuli are encoded into the trains of neuronal spikes that transmit the information to the brain to produce perception. However, is all the visual scene information required to explain the neuronal responses? In this work, we search for answers t…

Cited by 2SourcePDFScholar