Continual Learning

Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and shown to reduce forgetting. Furthermore, CL models deployed in mission-critical settings can benefit from uncertainty awareness by calibrating their predictions to reliably assess their confidences. However, existing uncertainty-aware continual learning methods suffer from high computational overhead and incompatibility with mainstream replay methods. To address this, we propose idempotent experience replay (IDER), a novel approach based on the idempotent property where repeated function applications yield the same output. Specifically, we first adapt the training loss to make model idempotent on current data streams. In addition, we introduce an idempotence distillation loss. We feed the output of the current model back into the old checkpoint and then minimize the distance between this reprocessed output and the original output of the current model. This yields a simple and effective new baseline for building reliable continual learners, which can be seamlessly integrated with other CL approaches. Extensive experiments on different CL benchmarks demonstrate that IDER consistently improves prediction reliability while simultaneously boosting accuracy and reducing forgetting. Our results suggest the potential of idempotence as a promising principle for deploying efficient and trustworthy continual learning systems in real-world applications.Our code is available at https://github.com/YutingLi0606/Idempotent-Continual-Learning.

Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing attention in CL. Several LoRA-based CL methods reduce interference across tasks by separating their update spaces, typically building the new space from the estimated null space of past tasks. However, they (i) overlook task-shared directions, which suppresses knowledge transfer, and (ii) fail to capture truly effective task-specific directions since these ``null bases" of old tasks can remain nearly inactive for new task under correlated tasks. To address this, we study LoRA learning capability from a projection energy perspective, and propose Low-rank Decomposition and Adaptation (LoDA). It performs a task-driven decomposition to build general and truly task-specific LoRA subspaces by solving two energy-based objectives, decoupling directions for knowledge sharing and isolation. LoDA fixes LoRA down-projections on two subspaces and learns robust up-projections via a Gradient-Aligned Optimization (GAO) approach. After each task, before integrating the LoRA updates into the backbone, LoDA derives a closed-form recalibration for the general update, approximating a feature-level joint optimum along this task-shared direction. Experiments indicate that LoDA outperforms existing CL methods. Our code is available at https://github.com/HHHLF/LoDA_ICML2026.

Medical image segmentation models are typically optimised with voxel-wise losses that constrain predictions only in the output space. This leaves latent feature representations largely unconstrained, potentially limiting generalisation. We propose {SegReg}, a latent-space regularisation framework that operates on feature maps of U-Net models to encourage structured embeddings while remaining fully compatible with standard segmentation losses. Integrated with the nnU-Net framework, we evaluate SegReg on prostate, cardiac, and hippocampus segmentation and demonstrate consistent improvements in domain generalisation. Furthermore, we show that explicit latent regularisation improves continual learning by reducing task drift and enhancing forward transfer across sequential tasks without adding memory or any extra parameters. These results highlight latent-space regularisation as a practical approach for building more generalisable and continual-learning-ready models.

Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural memory methods promise lightweight updates with minimal forgetting. However, existing neural memory models typically assume a single fixed objective and homogeneous information streams, leaving users with no control over what the model remembers or ignores over time. To address this challenge, we propose a generalized neural memory system that performs flexible updates based on learning instructions specified in natural language. Our approach enables adaptive agents to learn selectively from heterogeneous information sources, supporting settings, such as healthcare and customer service, where fixed-objective memory updates are insufficient.

Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can lead to biased model updates and suboptimal performance across tasks. While recent continual learning studies have made progress in addressing catastrophic forgetting, the problem of fairness caused the imbalanced data remains largely underexplored. This paper presents a novel Fairness Direct Preference Optimization (FaiDPO or $φ$-DPO) framework for continual learning in LMMs. In particular, we first propose a new continual learning paradigm based on Direct Preference Optimization (DPO) to mitigate catastrophic forgetting by aligning learning with pairwise preference signals. Then, we identify the limitations of conventional DPO in imbalanced data and present a new $φ$-DPO loss that explicitly addresses distributional biases. We provide a comprehensive theoretical analysis demonstrating that our approach addresses both forgetting and data imbalance. Additionally, to enable $φ$-DPO-based continual learning, we construct pairwise preference annotations for existing benchmarks in the context of continual learning. Extensive experiments and ablation studies show the proposed $φ$-DPO achieves State-of-the-Art performance across multiple benchmarks, outperforming prior continual learning methods of LMMs.

Alleviating catastrophic forgetting while enabling further learning is a primary challenge in continual learning (CL). Orthogonal-based training methods have gained attention for their efficiency and strong theoretical properties, and many existing approaches enforce orthogonality through gradient projection. In this paper, we revisit orthogonality and exploit the fact that small singular values correspond to directions that are nearly orthogonal to the input space of previous tasks. Building on this principle, we introduce NESS (Null-space Estimated from Small Singular values), a CL method that applies orthogonality directly in the weight space rather than through gradient manipulation. Specifically, NESS constructs an approximate null space using the smallest singular values of each layer's input representation and parameterizes task-specific updates via a compact low-rank adaptation (LoRA-style) formulation constrained to this subspace. The subspace basis is fixed to preserve the null-space constraint, and only a single trainable matrix is learned for each task. This design ensures that the resulting updates remain approximately in the null space of previous inputs while enabling adaptation to new tasks. Our theoretical analysis and experiments on three benchmark datasets demonstrate competitive performance, low forgetting, and stable accuracy across tasks, highlighting the role of small singular values in continual learning. The code is available at https://github.com/pacman-ctm/NESS.

A universal audio representation should capture fine-grained speech cues and high-level semantics for environmental sounds and music in a single encoder. Existing encoders often excel in one domain but degrade in others. We propose UniWhisper, an efficient continual multi-task training framework that casts heterogeneous audio tasks into a unified instruction and answer format. This enables standard next-token training without task-specific heads and losses. We train it on 38k hours of public audio and assess the encoder using shallow MLP probes and k-nearest neighbors (kNN) on 20 tasks spanning speech, environmental sound, and music. UniWhisper reaches normalized weighted averages of 0.81 with MLP probes and 0.61 with kNN, compared to 0.64 and 0.46 for Whisper, while retaining strong speech performance.

Solving the alternating current power flow equations in real time is essential for secure grid operation, yet classical Newton-Raphson solvers can be slow under stressed conditions. Existing graph neural networks for power flow are typically trained on a single system and often degrade on different systems. We present PowerModelsGAT-AI, a physics-informed graph attention network that predicts bus voltages and generator injections. The model uses bus-type-aware masking to handle different bus types and balances multiple loss terms, including a power-mismatch penalty, using learned weights. We evaluate the model on 14 benchmark systems (4 to 6,470 buses) and train a unified model on 13 of these under N-2 (two-branch outage) conditions, achieving an average normalized mean absolute error of 0.89% for voltage magnitudes and R^2 > 0.99 for voltage angles. We also show continual learning: when adapting a base model to a new 1,354-bus system, standard fine-tuning causes severe forgetting with error increases exceeding 1000% on base systems, while our experience replay and elastic weight consolidation strategy keeps error increases below 2% and in some cases improves base-system performance. Interpretability analysis shows that learned attention weights correlate with physical branch parameters (susceptance: r = 0.38; thermal limits: r = 0.22), and feature importance analysis supports that the model captures established power flow relationships.

The magnitude of parameter updates are considered a key factor in continual learning. However, most existing studies focus on designing diverse update strategies, while a theoretical understanding of the underlying mechanisms remains limited. Therefore, we characterize model's forgetting from the perspective of parameter update magnitude and formalize it as knowledge degradation induced by task-specific drift in the parameter space, which has not been fully captured in previous studies due to their assumption of a unified parameter space. By deriving the optimal parameter update magnitude that minimizes forgetting, we unify two representative update paradigms, frozen training and initialized training, within an optimization framework for constrained parameter updates. Our theoretical results further reveals that sequence tasks with small parameter distances exhibit better generalization and less forgetting under frozen training rather than initialized training. These theoretical insights inspire a novel hybrid parameter update strategy that adaptively adjusts update magnitude based on gradient directions. Experiments on deep neural networks demonstrate that this hybrid approach outperforms standard training strategies, providing new theoretical perspectives and practical inspiration for designing efficient and scalable continual learning algorithms.

Rehearsal is one of the key techniques for mitigating catastrophic forgetting and has been widely adopted in continual learning algorithms due to its simplicity and practicality. However, the theoretical understanding of how rehearsal scale influences learning dynamics remains limited. To address this gap, we formulate rehearsal-based continual learning as a multidimensional effectiveness-driven iterative optimization problem, providing a unified characterization across diverse performance metrics. Within this framework, we derive a closed-form analysis of adaptability, memorability, and generalization from the perspective of rehearsal scale. Our results uncover several intriguing and counterintuitive findings. First, rehearsal can impair model's adaptability, in sharp contrast to its traditionally recognized benefits. Second, increasing the rehearsal scale does not necessarily improve memory retention. When tasks are similar and noise levels are low, the memory error exhibits a diminishing lower bound. Finally, we validate these insights through numerical simulations and extended analyses on deep neural networks across multiple real-world datasets, revealing statistical patterns of rehearsal mechanisms in continual learning.

Continual learning systems are increasingly deployed in environments where retraining or reset is infeasible, yet many approaches emphasize task performance rather than the evolution of internal representations over time. In this work, we study a minimal continual learning agent designed to isolate representational dynamics from architectural complexity and optimization objectives. The agent maintains a persistent state vector across executions and incrementally updates it as new textual data is introduced. We quantify representational change using cosine similarity between successive normalized state vectors and define a stability metric over time intervals. Longitudinal experiments across eight executions reveal a transition from an initial plastic regime to a stable representational regime under consistent input. A deliberately introduced semantic perturbation produces a bounded decrease in similarity, followed by recovery and restabilization under subsequent coherent input. These results demonstrate that meaningful stability plasticity tradeoffs can emerge in a minimal, stateful learning system without explicit regularization, replay, or architectural complexity. The work establishes a transparent empirical baseline for studying representational accumulation and adaptation in continual learning systems.

Generalization is often regarded as an essential property of machine learning systems. However, perhaps not every component of a system needs to generalize. Training models for generalization typically produces entangled representations at the boundaries of entities or classes, which can lead to destructive interference when rapid, high-magnitude updates are required for continual or few-shot learning. Techniques for fast learning with non-interfering representations exist, but they generally fail to generalize. Here, we describe a Complementary Learning System (CLS) in which the fast learner entirely foregoes generalization in exchange for continual zero-shot and few-shot learning. Unlike most CLS approaches, which use episodic memory primarily for replay and consolidation, our fast, disentangled learner operates as a parallel reasoning system. The fast learner can overcome observation variability and uncertainty by leveraging a conventional slow, statistical learner within an active perception system: A contextual bias provided by the fast learner induces the slow learner to encode novel stimuli in familiar, generalized terms, enabling zero-shot and few-shot learning. This architecture demonstrates that fast, context-driven reasoning can coexist with slow, structured generalization, providing a pathway for robust continual learning.

Clinical deployment of chest radiograph classifiers requires models that can be updated as new datasets become available without retraining on previously observed data or degrading validated performance. We study a task-incremental continual learning setting for chest radiograph classification under task-unknown inference, where heterogeneous chest X-ray datasets arrive sequentially and task identity is unavailable at deployment time. We propose CARL-CXR, a continual adapter-based routing framework that maintains a fixed high-capacity backbone while incrementally introducing lightweight task-specific adapters and classifier heads. A latent task selector operates on adapter-conditioned features to dynamically route each input to the most relevant task pathway, leveraging compact task prototypes and feature-level experience replay to preserve task identity across sequential updates without storing raw images. Experiments on MIMIC-CXR and CheXpert two large-scale datasets with distinct patient populations, imaging devices, and annotation pipelines demonstrate that CARL-CXR achieves minimal catastrophic forgetting (0.012 AUROC drop), representing a 6X and 11X reduction over established continual learning baselines LwF and EWC respectively, while maintaining competitive diagnostic performance (AUROC 0.74). Under task unknown deployment, CARL-CXR outperforms joint training by 12.5 points in routing accuracy (75.0% vs. 62.5%): unlike LwF and EWC, which require explicit task identifiers at inference and provide no routing mechanism.

Continual learning remains constrained by the need for repeated retraining, high computational costs, and the persistent challenge of forgetting. These factors significantly limit the applicability of continuous learning in real-world settings, as iterative model updates require significant computational resources and inherently exacerbate forgetting. We present SAILS -- Segment Anything with Incrementally Learned Semantics, a training-free framework for Class-Incremental Semantic Segmentation (CISS) that sidesteps these challenges entirely. SAILS leverages foundational models to decouple CISS into two stages: Zero-shot region extraction using Segment Anything Model (SAM), followed by semantic association through prototypes in a fixed feature space. SAILS incorporates selective intra-class clustering, resulting in multiple prototypes per class to better model intra-class variability. Our results demonstrate that, despite requiring no incremental training, SAILS typically surpasses the performance of existing training-based approaches on standard CISS datasets, particularly in long and challenging task sequences where forgetting tends to be most severe. By avoiding parameter updates, SAILS completely eliminates forgetting and maintains consistent, task-invariant performance. Furthermore, SAILS exhibits positive backward transfer, where the introduction of new classes can enhance performance on previous classes.

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates, rather than considering what properties make the current task-specific update naturally preserve previously acquired knowledge. From a knowledge-decomposition perspective, we observe that low-rank adaptations exhibit highly imbalanced singular value spectra: a few dominant components absorb most of the adaptation energy, thereby (i) more likely to disrupt previously acquired knowledge and (ii) making the update more vulnerable to interference from subsequent tasks. To enable explicit balance among components, we decouple the magnitude of the task update from its directional structure and formulate it as a constrained optimization problem on a restricted Stiefel manifold. We address this problem using a projected first-order method compatible with standard deep-learning optimizers used in vision-language models. Our method mitigates both backward and forward forgetting, consistently outperforming continual learning baselines. The implementation code is available at https://github.com/haodotgu/EBLoRA.

Federated Continual Learning (FCL) leverages inter-client collaboration to better balance new knowledge acquisition and old knowledge retention on non-stationary data. However, existing FCL methods struggle to adapt to streaming scenarios where sequential and ephemerally accessible data chunks lack task identifiers and exhibit arbitrary class overlap, leading to confusion between old and new knowledge and an inability to sustain local inference on all encountered classes. To address this, we propose FedKACE with three components: 1) an adaptive mechanism that determines when to switch the inference model from the local to the global one to improve client-side inference performance; 2) a responsive gradient-balanced replay scheme that utilizes the ratio of the squared L2 gradient norms to balance client-specific knowledge between new acquisition and old retention; 3) a holistic buffer maintenance strategy that preserves highly informative and boundary-significant samples to enhance knowledge retention under class overlap.Experiments across multiple scenarios and theoretical analysis demonstrate the effectiveness of FedKACE.

Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters uniformly, failing to distinguish between specific task knowledge and shared capabilities. We introduce Mixture of Sparse Experts for Task-Agnostic Continual Learning (SETA), a framework that resolves the plasticity-stability conflict through adaptive sparse subspace decomposition into task-specific expert modules. Unlike standard updates, where tasks compete for the same parameters, SETA separates knowledge into unique experts, designed to isolate task-specific patterns, and shared experts, responsible for capturing common features. SETA shares an overlapping parameter block only when the new task's update passes a subspace-agreement test and a sign test against its prior expert; shared knowledge is protected by adaptive elastic anchoring, and independently gated routers retrieve the relevant experts at inference without task identifiers. Extensive experiments across diverse domain-specific benchmarks demonstrate that SETA achieves competitive or superior overall performance relative to state-of-the-art continual learning baselines, improving overall performance over the strongest baseline by 1.1 to 1.7 points on TRACE and by up to 5.5 points on the O-LoRA benchmark, with backward transfer between -2.2 and -1.3 on TRACE, against 4.6 to 6.3 points of forgetting for MoE-CL and 8 to 15 points for the other LoRA baselines.

Continual learning systems face a fundamental geometric obstacle: as experience accumulates on a fixed-capacity manifold, covering numbers grow linearly with time, eventually forcing representational overlap and catastrophic interference. Prevailing approaches attack this problem by expansion - projecting into higher-dimensional spaces via kernels, overparameterization, or replay. We argue the solution is the opposite: contraction. We formalize abstraction as the Urysohn Ladder, a hierarchy of quotient maps that recursively collapse validated metric neighborhoods into compact tokens, converting unbounded ambient-space search into bounded navigation on a low-dimensional intrinsic scaffold. Geometrically, each collapsed token acts as a shortcut - a region of extreme metric contraction that bridges distant experiences, much like a wormhole in the representational manifold. We establish four results that collectively guarantee separability (metric contraction renders nonlinearly entangled structure linearly separable at each quotient level, and this separability propagates faithfully through the entire hierarchy), bounded capacity (covering numbers remain $O(1)$ per quotient level, independent of stream length), stability (parity-partitioned flow/scaffold subspaces enable unbounded plasticity without catastrophic interference), and scalability (inference cost scales with quotient distance, not ambient distance). We validate each claim empirically with pretrained models and real-world datasets. Moreover, we demonstrate the potential of Urysohn Ladder for scalable continual learning via scaffold amortization.

Memory consolidation determines both what a learner can do now and which changes remain implementable later. We develop a finite-model synthesis of operational state abstraction and optimal control under the stability-evidence-revision (SER) framework. ``Poincaré meets Bellman'' names two complementary roles: qualitative dynamics identifies reusable action-response structure, and dynamic programming prices acquisition, retention, reuse, merging, and forgetting. Recurrence enters separately through the timing and value of future demands. We distinguish active quotient merging from historical information erasure, characterize exact repair by zero-error functional coding and causal migration, and derive a Bellman recursion over the joint law of hidden state and complete deployed memory. A first-return model yields an explicit retention rule. Conditional results show how factor sharing avoids enumerating combinations and how independent informative observations improve identification, while leaving some zero-error evidence budgets unchanged. Finite enumerations verify the coding and retention calculations. The synthesis gives an exact benchmark for specified finite models, without claiming universal recurrence, bounded-memory open-ended learning, or tractable global planning.

In order to achieve Continual Learning (CL), the problem of catastrophic forgetting, one that has plagued neural networks since their inception, must be overcome. The evaluation of continual learning methods relies on splitting a known homogeneous dataset and learning the associated tasks one after the other. We argue that most CL methods introduce a priori information about the data to come and cannot be considered agnostic. We exemplify this point with the case of methods relying on pretrained feature extractors, which are still used in CL. After showing that pretrained feature extractors imply a loss of generality with respect to the data that can be learned by the model, we then discuss other kinds of a priori information introduced in other CL methods. We then present the Online Patch Redundancy Eliminator (OPRE), an online dataset-compression algorithm that discards information through two explicit, input-space criteria. With a classifier that was randomly initialized at test time, OPRE's performance matches reported state-of-the-art online continual-learning methods on CIFAR 10 and CIFAR-100 without any pretrained feature extractor, and outperforms GDumb at an identical memory budget-while making only minimal and interpretable assumptions about the data to come. We frame these results as an empirical, information-theoretic perspective on continual learning.

Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation. A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios, which limits the generalization of conventional methods. We introduce Continual AQA (CAQA), which equips AQA with Continual Learning (CL) capabilities to handle evolving distributions while mitigating catastrophic forgetting. Although parameter-efficient fine-tuning of pretrained models has shown promise in continual learning, our empirical study shows that the evaluated adapter-based PEFT setting provides less effective downstream adaptation than FPFT for fine-grained AQA. Our empirical and theoretical analyses reveal two insights: (i) sufficiently expressive backbone adaptation is important for bridging the upstream--downstream representation gap; yet (ii) uncontrolled FPFT may induce overfitting and feature manifold shift, thereby aggravating forgetting. To address this, we propose Adaptive Manifold-Aligned Graph Regularization (MAGR++), which couples backbone fine-tuning that stabilizes shallow layers while adapting deeper ones with a two-step feature rectification pipeline: a manifold projector to translate deviated historical features into the current representation space, and a graph regularizer to align local and global distributions. We construct four CAQA benchmarks from three datasets with tailored evaluation protocols and strong baselines, enabling systematic cross-dataset comparison. Extensive experiments show that MAGR++ achieves state-of-the-art performance, with average correlation gains of 3.6% offline and 12.2% online over the strongest baseline, confirming its robustness and effectiveness.

Medical AI systems must remain reliable as data distributions shift across hospitals, imaging devices, and patient populations, yet privacy constraints often prevent storing or revisiting past patient data. We present UniPrompt-CL, a rehearsal-free domain-incremental learning framework for medical image classification using a single backbone and a single inference. Rather than relying on multiple backbones, repeated ViT inferences, or independent layer-wise prompt pools, UniPrompt-CL shares a unified prompt pool across transformer layers and expands it with only a few prompts per new domain. This reduces cross-layer redundancy while enabling efficient adaptation. On diabetic retinopathy, UniPrompt-CL improves average accuracy by 2.0 percentage points and substantially reduces forgetting relative to the strongest backbone-matched baseline. On skin cancer, it achieves competitive accuracy at the lowest training cost among DINOv2-B configurations. A controlled comparison varying only pool organization shows that the benefit arises from retention rather than learning each new domain: it is largest on the medical benchmarks, smaller on OfficeHome, and reverses on a heterogeneous six-stage DomainNet stream. These results suggest that cross-layer prompt sharing with lightweight expansion is practical for medical models requiring repeated retraining under limited on-site compute, while identifying the domain shifts under which it helps.

Recent work in continual learning has highlighted the stability gap -- a temporary performance drop on previously learned tasks when new ones are introduced. This phenomenon reflects a mismatch between rapid adaptation and strong retention at task boundaries, underscoring the need for optimization mechanisms that balance plasticity and stability over abrupt distribution changes. While optimizers such as momentum-SGD and Adam introduce implicit multi-timescale behavior, they still exhibit pronounced stability gaps. Importantly, these gaps persist even under ideal joint training, making it crucial to study them in this setting to isolate their causes from other sources of forgetting. Motivated by how noradrenergic (neuromodulatory) bursts transiently increase neuronal gain under uncertainty, we introduce a dynamic gain scaling mechanism as a two-timescale optimization technique that balances adaptation and retention by transiently increasing the effective update magnitude while dynamically reparameterizing the weights governing the forward pass, thereby empirically mitigating transition-induced curvature amplification. Across domain- and class-incremental MNIST, CIFAR, and mini-ImageNet benchmarks under task-agnostic joint training, dynamic gain scaling effectively attenuates stability gaps while maintaining competitive accuracy, improving robustness at task transitions.

Continual learning is an online paradigm where a learner continually accumulates knowledge from different tasks encountered over sequential time steps. Importantly, the learner is required to extend and update its knowledge without forgetting about the learning experience acquired from the past, and while avoiding the need to retrain from scratch. Given its sequential nature and its resemblance to the way humans think, continual learning offers an opportunity to address several challenges which currently stand in the way of widening the range of applicability of deep models to further real-world problems. The continual need to update the learner with data arriving sequentially strikes inherent congruence between continual learning and Bayesian inference which provides a principal platform to keep updating the prior beliefs of a model given new data, without completely forgetting the knowledge acquired from the old data. This survey inspects different settings of Bayesian continual learning, namely task-incremental learning and class-incremental learning. We begin by discussing definitions of continual learning along with its Bayesian setting, as well as the links with related fields, such as domain adaptation, transfer learning and meta-learning. Afterwards, we introduce a taxonomy offering a comprehensive categorization of algorithms belonging to the Bayesian continual learning paradigm. Meanwhile, we analyze the state-of-the-art while zooming in on some of the most prominent Bayesian continual learning algorithms to date. Furthermore, we shed some light on links between continual learning and developmental psychology, and correspondingly introduce analogies between both fields. We follow that with a discussion of current challenges, and finally conclude with potential areas for future research on Bayesian continual learning.

Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new tasks) and stability (preserving past knowledge). Neural Architecture Search (NAS), a branch of AutoML, automates the design of the architecture of Deep Neural Networks and has shown success in static settings. However, existing NAS-based approaches to incremental learning often rely on expanding the model at every task, making them impractical in resource-constrained environments. In this work, we introduce SEAL, a NAS-based framework tailored for data-incremental learning, a scenario where disjoint data samples arrive sequentially and are not stored for future access. SEAL adapts the model structure dynamically by expanding it only when necessary, based on a capacity estimation metric. Stability is preserved through cross-distillation training after each expansion step. The NAS component jointly searches for both the architecture and the optimal expansion policy. Experiments across multiple benchmarks demonstrate that SEAL effectively reduces forgetting and enhances accuracy while allocating additional capacity only when required. These results highlight the promise of combining NAS and selective expansion for efficient, adaptive learning in incremental scenarios.

The ability to learn continuously in artificial neural networks (ANNs) is often limited by catastrophic forgetting, a phenomenon in which new knowledge becomes dominant. By taking mechanisms of memory encoding in neuroscience (i.e., engrams) as inspiration, we propose a novel approach that integrates stochastically-activated engrams as a gating mechanism for metaplastic binarized neural networks (mBNNs). This method leverages the computational efficiency of mBNNs combined with the robustness of probabilistic memory traces to mitigate forgetting and maintain the model's reliability. Previously validated metaplastic optimization techniques have been incorporated to further enhance synaptic stability. Compared to baseline binarized models and benchmark fully connected continual learning approaches, our method is the only strategy capable of achieving average accuracies over 70% in both class-incremental and domain-incremental MNIST benchmarks, matching full-precision state-of-the-art methods. Furthermore, we achieve a significant reduction in peak GPU and RAM usage, under 5% and 20%, respectively, as well as an ~8x reduction in memory footprint compared to full precision counterparts. Our findings demonstrate (A) an improved stability vs. plasticity trade-off, (B) reduced memory intensiveness, and (C) enhanced performance in binarized architectures. By uniting principles of neuroscience and efficient computing, we offer new insights into the design of scalable and robust deep learning systems.

Continuous adaptive learning, the ability to adapt to the environment and keep improving performance, is a hallmark of natural intelligence. Biological organisms excel in acquiring, transferring, and retaining knowledge while adapting to volatile environments, making them a source of inspiration for artificial neural networks (ANNs). This study explores how neuromodulation, a building block of learning in biological systems, can help address catastrophic forgetting and enhance the robustness of ANNs in continual learning. Driven by neuromodulators including dopamine (DA), acetylcholine (ACh), serotonin (5-HT) and noradrenaline (NA), neuromodulatory processes in the brain operate at multiple scales, facilitating dynamic responses to environmental changes through mechanisms ranging from local synaptic plasticity to global network-wide adaptability. Importantly, the relationship between neuromodulators and their interplay in modulating sensory and cognitive processes is more complex than previously expected, demonstrating a "many-to-many" neuromodulator-to-task mapping. To inspire neuromodulation-aware learning rules, we highlight (i) how multi-neuromodulatory interactions enrich single-neuromodulator-driven learning, (ii) the impact of neuromodulators across multiple spatio-temporal scales, and correspondingly, (iii) strategies for approximating and integrating neuromodulated learning processes in ANNs, and (iv) an architectural-general formulation of multi-neuromodulatory dynamics. We also present a conceptual study to showcase how neuromodulation-inspired mechanisms, such as DA-driven reward processing and NA-based cognitive flexibility, can enhance ANN performance in a Go/No-Go task. Though multi-scale neuromodulation, we aim to bridge the gap between biological and artificial learning, paving the way for ANNs with greater flexibility, robustness, and adaptability.

As new knowledge rapidly accumulates, language models (LMs) with pretrained knowledge quickly become obsolete. A common approach to updating LMs is fine-tuning them directly on new knowledge. However, recent studies have shown that fine-tuning for memorization may be ineffective in storing knowledge or may exacerbate hallucinations. In this work, we introduce a setting we call continual memorization, where a model must memorize and retain a set of factoids through multiple stages of fine-tuning on subsequent datasets. We characterized the forgetting patterns through extensive experiments and show that LMs widely suffer from forgetting, especially when needing to memorize factoids in the second stage. We posit that forgetting can be alleviated by modifying training dynamics: (1) protecting the memorization process when learning factoids or (2) reducing interference from subsequent training stages. Intriguingly, we find that mixing randomly generated word sequences or generic data sampled from pretraining corpora at different training stages effectively mitigates forgetting REMIX: Random and Generic Data Mixing). REMIX can recover performance from severe forgetting, outperforming replay methods and other continual learning baselines. We analyze how REMIX influences the learning process and find that robust memorization follows a distinct pattern: the model stores factoids in earlier layers than usual and diversifies the layers that retain them, which results in easier recall and manipulate of the learned factoids.

We present iTeach, a deployable system that lets any co-located human fix a robot's perception failures on the spot without expertise, a workstation, or offline retraining. The operator wears a mixed reality (MR) headset, sees the robot's segmentation predictions overlaid on the real scene, and corrects failures hands-free: rearranging objects (HumanPlay), annotating via gaze and voice, and triggering SAM2 backward mask propagation. Each ~20 s interaction yields 150-300 densely labeled training frames; the system fine-tunes the perception model onboard, keeps the better model, and redeploys, all without leaving the deployment site. The full loop requires only an RGB-D camera, onboard GPU, and an MR headset: any mobile robot, any environment. Starting from 26.1 on cluttered real-world scenes, 45 teaching interactions (13K frames) raise segmentation to 80.7 with no catastrophic forgetting; on three standard benchmarks the model never trained on, performance improves as well. Downstream pick-and-place on SceneReplica reaches 72/100, surpassing a model-based pipeline requiring CAD models. A 12-participant user study confirms non-experts match experts on annotation accuracy (~95% box IoU), speed, and task load (NASA-TLX 21/100). The framework is architecture-agnostic: any fine-tunable perception model can serve as backbone.

A novel Learning-by-Education Node Community framework (LENC) for Collaborative Knowledge Distillation (CKD) is presented, which facilitates continual collective learning through effective knowledge exchanges among diverse deployed Deep Neural Network (DNN) peer nodes. These DNNs dynamically and autonomously adopt either the role of a student, seeking knowledge, or that of a teacher, imparting knowledge, fostering a collaborative learning environment. The proposed framework triggers knowledge transfer via autonomous teacher discovery and stream-driven DNN distillation as needed, while enhancing their learning capabilities and promoting their collaboration. LENC addresses the challenges of handling diverse training data distributions and the limitations of individual DNN node learning abilities. \hl{It enables the exploitation of selected peer-teacher knowledge upon learning a new task and mitigates catastrophic forgetting in DNN nodes.} \hl{Additionally, it supports task-boundary-free continual adaptation in distributed settings via autonomous role assignment and modular forgetting mitigation, as DNN nodes receive no explicit task-boundary metadata during deployment.} Experimental evaluation on a proof-of-concept implementation demonstrates the LENC framework's functionalities and benefits across multiple DNN learning and inference scenarios. The conducted experiments showcase its ability to gradually improve the average test accuracy of the community of interacting DNN nodes in image classification problems, by appropriately leveraging the collective knowledge of all node peers. The LENC framework achieves strong performance in on-line unlabelled CKD.