arXiv subjects

Mónika Farsang

Publications and source records attributed to Mónika Farsang.

14 recordsLinked to original sources

arXiv2026

Reshape and Recur: Improving SSMs with Input Reshaping and Depth Recurrence

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 Language Models (LLMs). These three advantages are a direct consequence of the time recurrence inherent in the SSMs architecture. Here, we further improve this recurrent architecture by positively answering two previously underexplored, orthogonal questions: (1) Can we reduce SSMs memory-footprint without any performance penalty, by also employing depth recurrence? (2) Can we increase SSMs performance by using a fixed and consistent time-granularity across all tasks? The first question is somewhat unexpected, given that SSMs are already recurrent. However, the orthogonal depth recurrence further decreases SSMs memory footprint. We show that a looped SSM with $k$ parameters adaptively iterated $M$ times, achieves a performance comparable to a standard SSM with $k \cdot L$ independent parameters, where $M \leq L$. The second question is also unexpected given the time-recurrent nature of the SSMs architecture. However, it makes perfect sense for the time-parallel training of SSMs on the entire input sequence. We show that concatenating time steps for lower-dimensional sequence elements, or flattening and re-chunking the joint feature-time dimension for high-dimensional ones, can improve the baseline by enhancing the way information is presented to the model. Our results for both extensions lead to consistent benefits across four representative SSM architectures: LRU, S5, LinOSS, LrcSSM.

cs.LG↗

arXiv2026

Riccati State Space Models: Non-iterative Parallelization for Nonlinear Sequence Modeling

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 parallel scan. Nonlinear recurrent models can provide richer, state-dependent dynamics, but generally lose this compositional structure: parallel evaluation then requires iterative methods that repeatedly linearize and scan the recurrence. We ask, what state-dependent nonlinear dynamics can be designed to remain exactly composable? We answer by introducing RiccatiSSM, a nonlinear SSM, in which each state dimension follows an input-conditioned Riccati differential equation. Its quadratic state dependence makes the local Jacobian explicitly state-dependent, while its exact per-step flow under piecewise-constant inputs is a Möbius transformation. Since Möbius maps are closed under composition and compose through $2\times 2$ matrix multiplication, the complete nonlinear state trajectory can be evaluated exactly with a single associative parallel scan, without iterative linearization. We further derive a constrained parameterization that ensures bounded, contractive dynamics, and avoids poles in the fractional-linear state update. Across long-sequence classification, regression, and forecasting tasks, RiccatiSSM achieves competitive predictive performance while reducing runtime by $22{-}33\%$ compared to the nonlinear LrcSSM under matched architectures. These results demonstrate that state-dependent nonlinear dynamics can retain exact composability and be evaluated efficiently within a single parallel scan.

cs.LG↗

arXiv2026

Adaptive Control in Autonomous Driving via Real-Time Recurrent RL

We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that updates policy parameters at every time step without backpropagation through time. We extend RTRRL to support LrcSSM, a recently proposed nonlinear diagonal state-space model, and combine offline behavioral cloning with online RTRRL fine-tuning to adapt policies to distribution shifts at deployment. We validate the approach in the CarRacing simulation and on a 1:10-scale RoboRacer platform equipped with an event camera, where a pretrained policy is fine-tuned online during real-world line-following. To our knowledge, this is the first demonstration of online RL fine-tuning with event-camera observations on standard (non-spiking) hardware in closed-loop control. LrcSSM-based policies improve fastest and most consistently across both settings.

cs.RO↗

arXiv2026

Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling

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 embedded hardware, especially when models are complex or horizons are long. Learning-based NMPC approximations shift this computation offline but typically demand large expert datasets and costly training. We propose Sequential-AMPC, a sequential neural policy that generates MPC candidate control sequences by sharing parameters across the prediction horizon. For deployment, we wrap the policy in a safety-augmented online evaluation and fallback mechanism, yielding Safe Sequential-AMPC. Compared to a naive feedforward policy baseline across several benchmarks, Sequential-AMPC requires substantially fewer expert MPC rollouts and yields candidate sequences with higher feasibility rates and improved closed-loop safety. On high-dimensional systems, it also exhibits better learning dynamics and performance in fewer epochs while maintaining stable validation improvement where the feedforward baseline can stagnate.

cs.LG↗

arXiv2026

Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models

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-extended models lead to interpretable behavior even in dense, all-to-all recurrent neural network (RNN) policies. We further demonstrate that incorporating chemical synapses improves interpretability and that combining chemical synapses with synaptic activation yields the most accurate and interpretable RNN models. To assess the accuracy and interpretability of these RNN policies, we consider the challenging lane-keeping control task and evaluate performance across multiple metrics, including turn-weighted validation loss, neural activity during driving, absolute correlation between neural activity and road trajectory, saliency maps of the networks' attention, and the robustness of their saliency maps measured by the structural similarity index.

cs.NE↗

arXiv2025

Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling

We present LrcSSM, a $\textit{non-linear}$ recurrent model that processes long sequences as fast as today's linear state-space layers. By forcing its Jacobian matrix to be diagonal, the full sequence can be solved in parallel, giving $\mathcal{O}(TD)$ computational work and memory and only $\mathcal{O}(\log T)$ sequential depth, for input-sequence length $T$ and a state dimension $D$. Moreover, LrcSSM offers a formal gradient-stability guarantee that other input-varying systems such as Liquid-S4 and Mamba do not provide. Importantly, the diagonal Jacobian structure of our model results in no performance loss compared to the original model with dense Jacobian, and the approach can be generalized to other non-linear recurrent models, demonstrating broader applicability. On a suite of long-range forecasting tasks, we demonstrate that LrcSSM outperforms Transformers, LRU, S5, and Mamba.

cs.LG↗

arXiv2025

Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents

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 input with depth information significantly enhances our agents' ability to predict steering commands compared to using RGB alone. We benchmark lightweight recurrent controllers that leverage the fused RGB-D features for sequential decision-making. To train our models, we collect high-quality data using a small-scale autonomous car controlled by an expert driver via a physical steering wheel, capturing varying levels of steering difficulty. Our models were successfully deployed on real hardware and inherently avoided dynamic and static obstacles, under out-of-distribution conditions. Specifically, our findings reveal that the early fusion of depth data results in a highly robust controller, which remains effective even with frame drops and increased noise levels, without compromising the network's focus on the task.

cs.RO↗

arXiv2025

Differential Gated Self-Attention

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 by lateral inhibition in biological neural circuits and building on the recent use by the Differential Transformer's use of two parallel softmax subtraction for noise cancellation, we propose Multihead Differential Gated Self-Attention (M-DGSA) that learns per-head input-dependent gating to dynamically suppress attention noise. Each head splits into excitatory and inhibitory branches whose dual softmax maps are fused by a sigmoid gate predicted from the token embedding, yielding a context-aware contrast enhancement. M-DGSA integrates seamlessly into existing Transformer stacks with minimal computational overhead. We evaluate on both vision and language benchmarks, demonstrating consistent robustness gains over vanilla Transformer, Vision Transformer, and Differential Transformer baselines. Our contributions are (i) a novel input-dependent gating mechanism for self-attention grounded in lateral inhibition, (ii) a principled synthesis of biological contrast-enhancement and self-attention theory, and (iii) comprehensive experiments demonstrating noise resilience and cross-domain applicability.

cs.LG↗

arXiv2025

Liquid Resistance Liquid Capacitance Networks

We introduce liquid-resistance liquid-capacitance neural networks (LRCs), a neural-ODE model which considerably improve the generalization, accuracy, and biological plausibility of electrical equivalent circuits (EECs), liquid time-constant networks (LTCs), and saturated liquid time-constant networks (STCs), respectively. We also introduce LRC units (LRCUs), as a very efficient and accurate gated RNN-model, which results from solving LRCs with an explicit Euler scheme using just one unfolding. We empirically show and formally prove that the liquid capacitance of LRCs considerably dampens the oscillations of LTCs and STCs, while at the same time dramatically increasing accuracy even for cheap solvers. We experimentally demonstrate that LRCs are a highly competitive alternative to popular neural ODEs and gated RNNs in terms of accuracy, efficiency, and interpretability, on classic time-series benchmarks and a complex autonomous-driving lane-keeping task.

cs.NE↗

arXiv2025

MMDVS-LF: Multi-Modal Dynamic Vision Sensor and Eye-Tracking Dataset for Line Following

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 machine learning algorithms remains limited. To address this gap and promote the development of models that leverage the specific characteristics of DVS data, we introduce the MMDVS-LF: Multi-Modal Dynamic Vision Sensor and Eye-Tracking Dataset for Line Following. This comprehensive dataset is the first to integrate multiple sensor modalities, including DVS recordings and eye-tracking data from a small-scale standardized vehicle. Additionally, the dataset includes RGB video, odometry, Inertial Measurement Unit (IMU) data, and demographic data of drivers performing a Line Following. With its diverse range of data, MMDVS-LF opens new opportunities for developing event-based deep learning algorithms just like the MNIST dataset did for Convolutional Neural Networks.

cs.RO↗

arXiv2023

Learning with Chemical versus Electrical Synapses -- Does it Make a Difference?

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 transmit neural signals, by enabling fast current flow between neurons. In contrast, bio-chemical synapses transmit neural signals indirectly, through neurotransmitters. Prior work showed that interpretable dynamics for complex robotic control, can be achieved by using chemical synapses, within a sparse, bio-inspired architecture, called Neural Circuit Policies (NCPs). However, a comparison of these two synaptic models, within the same architecture, remains an unexplored area. In this work we aim to determine the impact of using chemical synapses compared to electrical synapses, in both sparse and all-to-all connected networks. We conduct experiments with autonomous lane-keeping through a photorealistic autonomous driving simulator to evaluate their performance under diverse conditions and in the presence of noise. The experiments highlight the substantial influence of the architectural and synaptic-model choices, respectively. Our results show that employing chemical synapses yields noticeable improvements compared to electrical synapses, and that NCPs lead to better results in both synaptic models.

cs.NE↗

arXiv2023

Conditionally Risk-Averse Contextual Bandits

Contextual bandits with average-case statistical guarantees are inadequate in risk-averse situations because they might trade off degraded worst-case behaviour for better average performance. Designing a risk-averse contextual bandit is challenging because exploration is necessary but risk-aversion is sensitive to the entire distribution of rewards; nonetheless we exhibit the first risk-averse contextual bandit algorithm with an online regret guarantee. We conduct experiments from diverse scenarios where worst-case outcomes should be avoided, from dynamic pricing, inventory management, and self-tuning software; including a production exascale data processing system.

stat.ML↗

arXiv2021

Decaying Clipping Range in Proximal Policy Optimization

Proximal Policy Optimization (PPO) is among the most widely used algorithms in reinforcement learning, which achieves state-of-the-art performance in many challenging problems. The keys to its success are the reliable policy updates through the clipping mechanism and the multiple epochs of minibatch updates. The aim of this research is to give new simple but effective alternatives to the former. For this, we propose linearly and exponentially decaying clipping range approaches throughout the training. With these, we would like to provide higher exploration at the beginning and stronger restrictions at the end of the learning phase. We investigate their performance in several classical control and locomotive robotic environments. During the analysis, we found that they influence the achieved rewards and are effective alternatives to the constant clipping method in many reinforcement learning tasks.

cs.LG↗

arXiv2021

Importance of Environment Design in Reinforcement Learning: A Study of a Robotic Environment

An in-depth understanding of the particular environment is crucial in reinforcement learning (RL). To address this challenge, the decision-making process of a mobile collaborative robotic assistant modeled by the Markov decision process (MDP) framework is studied in this paper. The optimal state-action combinations of the MDP are calculated with the non-linear Bellman optimality equations. This system of equations can be solved with relative ease by the computational power of Wolfram Mathematica, where the obtained optimal action-values point to the optimal policy. Unlike other RL algorithms, this methodology does not approximate the optimal behavior, it gives the exact, explicit solution, which provides a strong foundation for our study. With this, we offer new insights into understanding the action selection mechanisms in RL by presenting various small modifications on the very same schema that lead to different optimal policies.

cs.LG↗