8 papers
Riccati State Space Models: Non-iterative Parallelization for Nonlinear Sequence Modeling
Mónika Farsang, Ramin Hasani, Daniela Rus +1
State space models (SSMs) achieve efficient sequence processing because their affine state updates are closed under composition and can therefore be evaluated with an associative p…
Reshape and Recur: Improving SSMs with Input Reshaping and Depth Recurrence
Mónika Farsang, Ramin Hasani, Daniela Rus +1
State Space Models (SSMs) are increasingly deployed in the Edge because they offer, at comparable performance, a smaller memory/training/inference footprint, compared to Large Lang…
Adaptive Control in Autonomous Driving via Real-Time Recurrent RL
Julian Lemmel, Felix Resch, Mónika Farsang +3
We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that update…
The Quest for Universal Master Key Filters in DS-CNNs
Zahra Babaiee, Peyman M. Kiassari, Daniela Rus +1
A recent study has proposed the "Master Key Filters Hypothesis" for convolutional neural network filters. This paper extends this hypothesis by radically constraining its scope to…
Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus +1
Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to rec…
The Master Key Filters Hypothesis: Deep Filters Are General
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus +1
This paper challenges the prevailing view that convolutional neural network (CNN) filters become increasingly specialized in deeper layers. Motivated by recent observations of clus…
Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus +1
Recent advances in depthwise-separable convolutional neural networks (DS-CNNs) have led to novel architectures, that surpass the performance of classical CNNs, by a considerable sc…
Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus +1
In this study, we present evidence suggesting that depthwise convolutional kernels are effectively replicating the structural intricacies of the biological receptive fields observe…