Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice, suffers from the truncation bias, which drastically limits its ability to learn long-term dependencies.The Real Time Recurrent Learning algorithm (RTRL) addresses this issue, but its high computational requirements make it infeasible in practice. The Unbiased Online Recurrent Optimization algorithm (UORO) approximates RTRL with a smaller runtime and memory cost, but with the disadvantage of obtaining noisy gradients that also limit its practical applicability. In this paper we propose the Kronecker Factored RTRL (KF-RTRL) algorithm that uses a Kronecker product decomposition to approximate the gradients for a large class of RNNs. We show that KF-RTRL is an unbiased and memory efficient online learning algorithm. Our theoretical analysis shows that, under reasonable assumptions, the noise introduced by our algorithm is not only stable over time but also asymptotically much smaller than the one of the UORO algorithm. We also confirm these theoretical results experimentally. Further, we show empirically that the KF-RTRL algorithm captures long-term dependencies and almost matches the performance of TBPTT on real world tasks by training Recurrent Highway Networks on a synthetic string memorization task and on the Penn TreeBank task, respectively. These results indicate that RTRL based approaches might be a promising future alternative to TBPTT.

A promising direction istouse linear recurrent architectures (LRUs), where dense recurrent weights are replaced with a complex-valued diagonal, making RTRL efficient.

Recurrent Neural Networks (RNNs) are used to learn representations in partially observable environments. For agents that learn online and continually interact with the environment, it is desirable to train RNNs with real-time recurrent learning (RTRL); unfortunately, RTRL is prohibitively expensive for standard RNNs. A promising direction is to use linear recurrent architectures (LRUs), where dense recurrent weights are replaced with a complex-valued diagonal, making RTRL efficient. In this work, we build on these insights to provide a lightweight but effective approach for training RNNs in online RL. We introduce Recurrent Trace Units (RTUs), a small modification on LRUs that we nonetheless find to have significant performance benefits over LRUs when trained with RTRL. We find RTUs significantly outperform GRUs and Transformers across several partially observable environments while using significantly less computation.

Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice, suffers from the truncation bias, which drastically limits its ability to learn long-term dependencies.The Real Time Recurrent Learning algorithm (RTRL) addresses this issue, but its high computational requirements make it infeasible in practice. The Unbiased Online Recurrent Optimization algorithm (UORO) approximates RTRL with a smaller runtime and memory cost, but with the disadvantage of obtaining noisy gradients that also limit its practical applicability. In this paper we propose the Kronecker Factored RTRL (KF-RTRL) algorithm that uses a Kronecker product decomposition to approximate the gradients for a large class of RNNs. We show that KF-RTRL is an unbiased and memory efficient online learning algorithm. Our theoretical analysis shows that, under reasonable assumptions, the noise introduced by our algorithm is not only stable over time but also asymptotically much smaller than the one of the UORO algorithm. We also confirm these theoretical results experimentally. Further, we show empirically that the KF-RTRL algorithm captures long-term dependencies and almost matches the performance of TBPTT on real world tasks by training Recurrent Highway Networks on a synthetic string memorization task and on the Penn TreeBank task, respectively. These results indicate that RTRL based approaches might be a promising future alternative to TBPTT.

Large Language Models (LLMs) are emerging as versatile foundation models for computational chemistry, handling bidirectional tasks like reaction prediction and retrosynthesis. However, these models often lack round-trip consistency. For instance, a state-of-the-art chemical LLM may successfully caption a molecule, yet be unable to accurately reconstruct the original structure from its own generated text. This inconsistency suggests that models are learning unidirectional memorization rather than flexible mastery. Indeed, recent work has demonstrated a strong correlation between a model's round-trip consistency and its performance on the primary tasks. We therefore introduce Round-Trip Reinforcement Learning (RTRL), a novel framework that trains a model to improve its consistency by using the success of a round-trip transformation as a reward signal. We further propose an iterative variant where forward and reverse mappings alternately train each other in a self-improvement loop, a process that is highly data-efficient and notably effective with the massive amount of unlabelled data common in chemistry. Experiments demonstrate that RTRL significantly boosts performance and consistency over strong baselines across supervised, self-supervised, and synthetic data regimes. This work shows that round-trip consistency is not just a desirable property but a trainable objective, offering a new path toward more robust and reliable foundation models. Large Language Models (LLMs) are emerging as a powerful class of versatile and generalizable foundation models for computational chemistry (Fang et al.; Cao et al., 2025; Wang et al., 2025). A key advantage is their ability to provide a more flexible and intuitive interface for scientists, enabling interaction with complex data through natural language. This is powered by their unique capability to process and generate information across diverse chemical modalities, from structured SMILES strings to unstructured experimental procedures (Zhao et al., 2025; Pei et al., 2024a). By unifying these disparate tasks and data types within a single framework, LLMs promise to significantly accelerate the pace of scientific discovery. A prominent theme enabled by this new generation of models is the modeling of bidirectional chemical tasks, such as translating between textual descriptions and molecular structures or mapping between forward synthesis and retrosynthesis (Pei et al., 2024b; Edwards et al., 2024; Liu et al., 2024). More than just a capability, however, this bidirectionality allows us to examine a model's depth of understanding through the crucial property of round-trip consistency (RTC).

Recurrent Neural Networks (RNNs) are used to learn representations in partially observable environments. For agents that learn online and continually interact with the environment, it is desirable to train RNNs with real-time recurrent learning (RTRL); unfortunately, RTRL is prohibitively expensive for standard RNNs. A promising direction is to use linear recurrent architectures (LRUs), where dense recurrent weights are replaced with a complex-valued diagonal, making RTRL efficient. In this work, we build on these insights to provide a lightweight but effective approach for training RNNs in online RL. We introduce Recurrent Trace Units (RTUs), a small modification on LRUs that we nonetheless find to have significant performance benefits over LRUs when trained with RTRL.

The manuscript describes a discrete time reduction of equilibrium prop (EP) which enables the authors to compare the algorithms gradient estimates and performance directly to BPTT. Moreover, the associated reduction in compute cost also enables them to train the first CNN (that I know of) using EP. While EP approximates BP in feedforward networks, it uses neuronal activity of an RNN in equilibrium to propagate target information or error feedback to perform credit assignment. While this work may be less interesting for DL practitioners because it is still more costly than backprop (BP), it is one of the contenders for bio-plausible backprop which is discussed in the literature. In that regard the present work contributes to this discussion meaningfully.

Online synaptic plasticity rules derived from gradient descent achieve high accuracy on a wide range of practical tasks. However, their software implementation often requires tediously hand-derived gradients or using gradient backpropagation which sacrifices the online capability of the rules. In this work, we present a custom automatic differentiation (AD) pipeline for sparse and online implementation of gradient-based synaptic plasticity rules that generalizes to arbitrary neuron models. Our work combines the programming ease of backpropagation-type methods for forward AD while being memory-efficient. To achieve this, we exploit the advantageous compute and memory scaling of online synaptic plasticity by providing an inherently sparse implementation of AD where expensive tensor contractions are replaced with simple element-wise multiplications if the tensors are diagonal. Gradient-based synaptic plasticity rules such as eligibility propagation (e-prop) have exactly this property and thus profit immensely from this feature. We demonstrate the alignment of our gradients with respect to gradient backpropagation on an synthetic task where e-prop gradients are exact, as well as audio speech classification benchmarks. We demonstrate how memory utilization scales with network size without dependence on the sequence length, as expected from forward AD methods.

Lung radiotherapy treatment systems are subject to a latency that leads to uncertainty in the estimated tumor location and high irradiation of healthy tissue. This work addresses future frame prediction in chest dynamic MRI sequences to compensate for that delay using RNNs trained with online learning algorithms. The latter enable networks to mitigate irregular movements, as they update synaptic weights with each new training example. Experiments were conducted using four publicly available 2D thoracic cine-MRI sequences. PCA decomposes the time-varying deformation vector field (DVF), computed with the Lucas-Kanade optical flow algorithm, into static deformation fields and low-dimensional time-dependent weights. We compare various algorithms to forecast the latter: linear regression, least mean squares (LMS), and RNNs trained with real-time recurrent learning (RTRL), unbiased online recurrent optimization, decoupled neural interfaces and sparse 1-step approximation (SnAp-1). That enables estimating the future DVFs and, in turn, the next frames by warping the initial image. Linear regression led to the lowest mean DVF error at a horizon h = 0.32s (the time interval in advance for which the prediction is made), equal to 1.30mm, followed by SnAp-1 and RTRL, whose error increased from 1.37mm to 1.44mm as h increased from 0.62s to 2.20s. Similarly, the structural similarity index measure (SSIM) of LMS decreased from 0.904 to 0.898 as h increased from 0.31s to 1.57s and was the highest among the algorithms compared for the latter horizons. SnAp-1 attained the highest SSIM for h $\geq$ 1.88s, with values of less than 0.898. The predicted images look similar to the original ones, and the highest errors occurred at challenging areas such as the diaphragm boundary at the end-of-inhale phase, where motion variability is more prominent, and regions where out-of-plane motion was more prevalent.