12 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…
Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling
Mihaela-Larisa Clement, Mónika Farsang, Agnes Poks +4
The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on…
Single molecule localization microscopy challenge: a biologically inspired benchmark for long-sequence modeling
Fatemeh Valeh, Monika Farsang, Radu Grosu +1
State space models (SSMs) have recently achieved strong performance on long sequence modeling tasks while offering improved memory and computational efficiency compared to transfor…
Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models
Mónika Farsang, Radu Grosu
In this paper, we present a unified framework for various bio-inspired models to better understand their structural and functional differences. We show that liquid-capacitance-exte…
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…
Differential Gated Self-Attention
Elpiniki Maria Lygizou, Mónika Farsang, Radu Grosu
Transformers excel across a large variety of tasks but remain susceptible to corrupted inputs, since standard self-attention treats all query-key interactions uniformly. Inspired b…
Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
Mónika Farsang, Ramin Hasani, Daniela Rus +1
We present LrcSSM, a recurrent model that processes long sequences as fast as today's linear state-space layers. By forcing its Jacobian matrix to be diagonal…
Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents
Mihaela-Larisa Clement, Mónika Farsang, Felix Resch +2
Autonomous agents that rely purely on perception to make real-time control decisions require efficient and robust architectures. In this work, we demonstrate that augmenting RGB in…
MMDVS-LF: Multi-Modal Dynamic Vision Sensor and Eye-Tracking Dataset for Line Following
Felix Resch, Mónika Farsang, Radu Grosu
Dynamic Vision Sensors (DVS) offer a unique advantage in control applications due to their high temporal resolution and asynchronous event-based data. Still, their adoption in mach…
Liquid Resistance Liquid Capacitance Networks
Mónika Farsang, Sophie A. Neubauer, Radu Grosu
We introduce liquid-resistance liquid-capacitance neural networks (LRCs), a neural-ODE model which considerably improve the generalization, accuracy, and biological plausibility of…
Learning with Chemical versus Electrical Synapses -- Does it Make a Difference?
Mónika Farsang, Mathias Lechner, David Lung +3
Bio-inspired neural networks have the potential to advance our understanding of neural computation and improve the state-of-the-art of AI systems. Bio-electrical synapses directly…