Overview

Continual Learning studies how models adapt to sequences of tasks or non-stationary data without losing useful earlier knowledge, a challenge known as catastrophic forgetting. Common approaches replay selected examples, regularize updates to protect important parameters, isolate tasks with adapters or separate subnetworks, or manage knowledge through prompts, memory, and model expansion. Methods are tested on class- and domain-incremental image benchmarks such as CIFAR and ImageNet, as well as task-free streams and applications in language, robotics, and healthcare. A central tension is balancing retention with the capacity to learn, while evaluations increasingly question assumptions such as known task boundaries and seek to measure transfer, recovery, resource use, and performance under realistic shifts.

Latest papers

323 papers26 papers in the last four weeks, down 24% on the four weeks before. 0.2% of all new papers.

Nov 12, 2026

Uncertainty-Aware Continual Learning for 2D XRD Interpretation Using Simulated and Experimental Data

Autonomous experimentation systems require characterization models that can interpret heterogeneous measurements and maintain predictive performance as data accumulate. Developing such models involves addressing domain mismatch between data sources, overconfident predictions on unfamiliar inputs, and catastrophic forgetting during sequential updates. In this work, we present a proof-of-concept framework for uncertainty-aware continual interpretation of two-dimensional X-ray diffraction (XRD) data. The framework integrates established components: maximum mean discrepancy-based domain adaptation to reduce simulation-to-experiment discrepancies, a convolutional neural network with a spectral-normalized neural Gaussian process (CNN--SNGP) for predictive uncertainty estimation, and replay with knowledge distillation for sequential model updating. We evaluate the framework using simulated and previously-collected experimental data for crystal structure classification of single-phase body-centered cubic, face-centered cubic, and hexagonal close-packed patterns. Data are organized into predefined sequential blocks to assess adaptation and retention of previously learned knowledge. Within this setting, the results show accurate classification across simulated and experimental data, improved alignment between the two domains, and reduced forgetting compared with naïve fine-tuning. Predictive uncertainty is also evaluated on unfamiliar and noisy inputs. The contribution is the integration and evaluation of these capabilities for sequential XRD interpretation. The framework provides a basis for future integration into autonomous experimentation systems, with experimental planning, instrument control, and closed-loop deployment remaining areas for future development.
Nov 10, 2026

Continual-ARC: Measuring Skill Acquisition over a Working Lifetime

Agent harnesses have emerged as a promising mechanism for continual learning, alongside test-time parametric learning. However, the current benchmarks have several limitations: they generally focus on a single applied domain, serve each instance only once, and assume a single family of learner, so memory-based and weight-based systems are rarely compared on the same scale. We propose Continual-ARC, a lifelong stream built from the three ARC-AGI editions, whose tasks need no domain knowledge. The same tasks return after dormant gaps with fresh instances, while new tasks keep arriving. On each instance, the learner may pay for demonstrations, submit answers, or act inside the harness, with retries permitted on incorrect submissions, which are paid for. Each instance is scored based on the share of this feedback budget consumed. Since a learner may keep anything between instances, memory-based and weight-based systems are scored on the same scale. After the stream, the learner is frozen and tested on fresh instances of the tasks it met, which measures memorization, and on unseen tasks, which measures generalization. We run an agent harness with frozen weights, with and without persistence, on Qwen3.5-9B and GLM-5.3 Flash, comparing them with two prompting floors, a program-induction method and Qwen3.5-9B's weights trained to imitate GLM-5.3 Flash. Persistence in the harness generally does not improve memorization unless provided with explicit expert guidance. Most harness-based methods still learn less than a floor that simply caches each task's demonstrations, across all models we tested. No harness-based method gains on unseen tasks, whereas weight-based learning shows substantial gains. This opens the door to future weight-based continual learning that could teach models to drive harnesses in new domains.
Nov 10, 2026

MEOW: Medical Open-World Interactive Segmentation

In open-world recognition, machine learning models not only make predictions on unknown structures ("generalized open-set"), but also continually learn and improve from those predictions over time. Interactive segmentation, despite its access to user feedback, has so far remained confined to the open-set setting. In this work we introduce MEOW, the first framework that turns non-interactive segmentation backbones into interactive open-world learners without updating learnable model parameters. MEOW combines parameter-free transductive reasoning with memory consolidation to accumulate knowledge and thereby improve future performance. Focusing on medical data, we show that MEOW consistently improves its own predictions on classes never seen during training, and transfers zero-shot to unfamiliar domains, including micro-CT data and other imaging modalities.
Nov 9, 2026

F3-AGI v4.0: Bioenergetically-Gated Active Inference, Metaplastic Preconditioning, and Residual Program Synthesis for Sample-Efficient Abstract Reasoning

Few-shot abstract reasoning on ARC-AGI requires inducing algorithmic transformations from 2 to 5 demonstration pairs without task-specific pretraining. Because few-shot demonstrations under-constrain the hypothesis space, program synthesis suffers from the Rashomon effect (predictive multiplicity): heuristic search finds spurious programs with low training error that fail on test inputs, while unconstrained library growth degrades latency. We introduce F3-AGI v4.0, a CPU-native neuro-symbolic and active inference architecture comprising three mechanisms: (1) F3-Metabolic-Optim, combining mistake-gated plasticity, Fisher-EMA preconditioning, and virtual ATP gating; (2) Adaptive Complexity-Guided Program Synthesis (AACR) with a Cycle-3 ResidualPatchSynthesizer and smallest-pair early rejection; and (3) a 512D L2-normalized random projection driving Expected Free Energy (EFE) exploration with dead-signature pruning. Across three empirical studies: (i) on a synthetic 5-task class-incremental stream without replay, F3-Metabolic-Optim achieves 91.67% final accuracy with 9.17% forgetting, skipping 93.47% of updates, cutting L1 plasticity cost by 65.7%, and running 2.19x faster than EWC; (ii) on the 400-task ARC-AGI-1 public evaluation set (offline CPU, zero LLM calls), F3-AGI v4.0 solves 57/400 tasks (14.25% pass@2; 56/400 pass@1) with a mean latency of 1.62 s/task, decomposed into 19/50 (38.00%, 1.19 s/task, a 42.5x paired speedup over Horizon 2) on the 50-task calibration slice and 38/350 (10.86%) on the 350 strictly uninspected hold-out tasks (with 7 autonomous Cycle-3 patch solutions); and (iii) in a local 5-game (15-level) ARC-AGI-3-inspired interactive suite, our agent completes 15/15 levels with 89.44% level-weighted RHAE (90.72% unweighted).
Nov 9, 2026

Anchor Behavior, Not Parameters: Rehearsal-Free Continual Learning with a Single Shared Prompt

Prompt-based continual learning adapts a frozen pre-trained vision transformer by tuning a small set of prompt tokens. Recently, one-prompt methods which share one single prompt across all tasks make this paradigm maximally parameter efficient. The open question is how a shared prompt can keep the knowledge of old classes while being updated for new ones. Existing methods protect old knowledge in parameter space, where they freeze task-specific prompts, expand new components, or sparsely gate which tokens receive gradients. However, this method sacrifices plasticity, yet the drift it still permits in shared tokens can corrupt the prompt's function on past classes. What must be preserved is the prompt's behavior. We propose TEA-Prompt, which couples (i) a token evaluation module that assigns each prompt token a continuous, input-conditional relevance score injected into the attention logits, softly specializing tokens across tasks without discarding any of them, and (ii) an attention-behavior anchoring loss that constrains each token's attention output around class-specific query regions using only compact Gaussian query statistics without stored old images, weighted by the token's past relevance. Anchoring the attention value allows the parameters to continue updating freely, as long as their interaction remains unchanged. TEA-Prompt achieves state-of-the-art accuracy with markedly lower forgetting on CIFAR-100, ImageNet-R, and CUB-200 with only 0.38M parameters. Code is publicy available at https://github.com/cuonga1cvp/TEA-Prompt.git
Nov 9, 2026

Autonomous Continual Learning and Knowledge Transfer via Cortex-Inspired Neural Assemblies

Unlike the brain, artificial neural networks (ANNs) suffer from "catastrophic forgetting": complete overwriting of solutions when re-training on new functions ("concept shift") or on a disjoint domain of the current function ("domain shift"). ANNs require each batch of data to be roughly representative of the complete distribution, a typically expensive and impractical requirement. In this paper, we introduce Functional Task Networks (FTNs), a method of continual learning and knowledge transfer modeled after several properties of the mammalian neocortex. FTN is formulated as a distributed, stochastic mixture of experts in which a sparse, binary routing mask is computed at inference time using a small support sample of input-output pairs. Per-batch reconfiguration of the router during training, together with mask-overlap-filtered replay, shapes a basis of overlapping, partially trained subnetworks. Unrelated tasks route through mostly separate assemblies, related tasks overlap on shared components. On block-sequentially trained continual learning and knowledge transfer tasks FTN retains solutions nearly as well as disjoint-mask isolation and attains the lowest pre-update head-start loss among matched-architecture comparators. The learned mask-overlap geometry tracks the known concept-sharing structure where available. We show experimentally that under correlated concept shift, support-set mask reconfiguration is necessary even for retention. Under domain shift, the distributed bank with replay is sufficient to handle retention without the configurer. Forward transfer, or head-start, and backward transfer, are also contributed by support-set mask configuration.
Nov 7, 2026

Unified Factored Representations Resist Catastrophic Forgetting

This paper explores an unexpected connection between the quality of a neural network's (NN's) internal representation and its vulnerability to catastrophic forgetting. The representational forgetting hypothesis is that networks with unified, factored representation (UFR) can resist catastrophic forgetting without any modification to the underlying fine-tuning algorithm or network architecture. The key insight is that catastrophic forgetting may largely result from fractured entangled representation (FER): fine-tuning on only part of the input domain results in disruptive changes for other input patterns, because of how individual features are globally entangled. In contrast, if a gradient update is compatible with how a UFR network factors its representation, such an update may result in coordinated change across the input domain, alleviating catastrophic forgetting. Experiments in two domains provide evidence for this hypothesis: (1) an illustrative 1D regression task, in which UFR networks constructed by hand are compared against networks trained from scratch with SGD, and (2) an image-regression task with NNs previously shown to exhibit UFR. In both settings, UFR networks forget substantially less than their FER counterparts when repeatedly fine-tuned on UFR-compatible variations. Further experiments show that a training loss that distills UFR representations into fresh NNs reduces forgetting; along with several additional controls, these results help isolate representation as the critical factor. Together these results suggest that representational quality is an underappreciated contributor to catastrophic forgetting, and that the encouragement and maintenance of such quality may require attending to what patterns a particular NN is ready to learn.
Nov 7, 2026

STABLE: A Continual Learning Optimizer with Adaptive Drift Control

Continual learning suffers from catastrophic forgetting, leading to the loss of past knowledge and unstable adaptation across task streams. Existing approaches typically address this issue through replay buffers, architectural changes, or additional regularization terms. We argue that forgetting is a consequence of unstable learning dynamics, which may benefit from an optimizer-level solution. The main challenge is that learning dynamics are time-dependent, as demonstrated by empirical phenomena such as the stability gap. First, we formally prove that, for distance-based classifiers, bounded parameter drift guarantees bounded margin erosion under a local score-stability condition. Based on this insight, we propose STABLE, a primal-dual optimizer with adaptive drift control. STABLE enforces a drift budget by increasing the dual variable when the budget is violated and decreasing it otherwise. This results in high stability without penalizing plasticity. Experiments on long-horizon unimodal streams and CLIP-based multimodal streams show that vanilla PEFT baselines trained with STABLE match or outperform specialized continual learning methods. In the multimodal setting, STABLE further preserves zero-shot transfer, matching or exceeding dedicated multimodal continual learning methods. Code is available at https://github.com/atlas-luiss/STABLE.
Nov 5, 2026

Permanent and Transient Representations for Continual Reinforcement Learning

Continual Reinforcement Learning (CRL) agents struggle to adapt to new situations while retaining prior knowledge, leading to a stability-plasticity trade-off. One approach to solving this problem is by using complementary learning systems: one for slow, long-term learning and another for quick, transient adaptation. Anand & Precup (2023) instantiated this idea using permanent and transient value functions, but used the same features in both systems. Intuitively, long-term learning should rely more on parametric representations for broad generalization, while transient learning would be best served by non-parametric representations for situation-specific adaptation. In this paper, we explore this idea both theoretically and empirically. By introducing a novel non-parametric approximation for estimating the transient value function in complex tasks, we demonstrate that our method enables online learning and outperforms competitive baselines on image-based tasks and Craftax-Classic, underscoring the effectiveness of our system-level decomposition.
Nov 4, 2026

Human Motion Prediction via Continual Prior Compensation

Human Motion Prediction (HMP) aims to predict future human poses at different moments according to observed past motion sequences. Previous approaches mainly treated the prediction of different temporal moments as a single prediction task and learned the predictions of varied moments simultaneously, which would encounter a main limitation: the learning of short-term predictions (referring to near-future'' prediction) could be hindered by the predictions of long-term (referring to far-future'' prediction) motions. In this paper, we develop a novel temporal continual learning framework called Continual Prior Compensation (CPC) to progressively train HMP models, in which we divide the prediction task of motions corresponding to varied temporal moments into several subtasks and train the model in a multi-stage manner. To mitigate the prior information forgetting in the progressive training, we further introduce a learnable random variable Prior Compensation Factor (PCF) to explicitly measure the prior knowledge loss. We theoretically show that the PCF can be efficiently learned together with the model parameters by minimizing a reasonable upper bound of the objective function. The proposed CPC is further enhanced to estimate the prior information loss for each subtask and a new framework called Continual Prior Compensation++ (CPC++) with Fine-Grained Prior Compensation Factor (FGPCF) is finally developed. Our CPC and CPC++ frameworks are quite flexible and can be easily integrated with different HMP backbone models and adapted to various datasets and applications. Extensive experiments on three HMP benchmark datasets using multiple SOTA HMP backbones (PGBIG, siMLPe, MotionMixer, and LTD) demonstrate the effectiveness and flexibility of our frameworks.
Nov 3, 2026

What Is the Influence of Task Order in Continual Learning? An Empirical Study and Order-Aware Evaluation for Motion Forecasting

Aggregate scores for continual learning algorithms rest on a distribution over task orders that is rarely stated. We formulate algorithm comparison as an expectation over a declared order distribution, which separates training variation from order variation, and apply it to motion forecasting with four road-layout tasks from the INTERACTION dataset, all 24 task orders, four algorithms, and three training replicates (288 runs). Task order accounts for 65% to 91% of the variation in current-task error and backward transfer, and 90% to 99% of this order effect comes from the identity of the starting task: the smallest task cannot be learned from a cold start. Beyond the first stage, the order effect is comparable to training variability. In most orders, the leading algorithm in current-task error and backward transfer is within one replicate standard deviation of the runner-up. Backward transfer depends on the order mainly through its reference term, which weights the first task most heavily, so relative improvement and final error identify different leading algorithms for displacement error. A transition-direction descriptor computed from task statistics tracks the position of the smallest task, and weighting orders by it leaves the algorithm ranking unchanged. These results call for benchmarks that declare their order distribution and report order-resolved, starting-task-resolved, warm-start, and final errors alongside aggregate scores. The code and data are available here.
Nov 1, 2026

HQNN-CL: Regime-Aware Hybrid Quantum Neural Network with Continual Learning for Financial Forecasting

Financial time-series forecasting is still difficult owing to the non-stationary nature of the market, regime changes, and catastrophic forgetting, which makes conventional deep learning models hard to adapt in the long term. To achieve uncertainty-aware robust financial forecasting in the face of changing market conditions, this study proposes a Hybrid Quantum-Classical Neural Network with Continual Learning (HQNN-CL). The proposed framework combines Gaussian Hidden Markov Model (HMM) based regime detection, BiLSTM temporal encoding, adaptive-depth parameterized quantum circuits, Elastic Weight Consolidation (EWC), experience replay, and probabilistic forecasting in a single architecture. The framework was tested on four real-time stock datasets: Microsoft, Systems Limited, Teradata and Tata Consultancy Services, and compared with seven state-of-the-art forecasting models, including recurrent and Transformer-based models. The experimental results show that HQNN-CL has outperformed other methods on the Systems Limited (RMSE = 3.0149) and Teradata (RMSE = 0.8909) datasets and is within 0.32% and 0.40% of the best baseline method for Microsoft and Tata Consultancy Services, respectively. The proposed framework also generates well-calibrated probabilistic forecasts within the range of 89.5% to 96.5% empirical coverage rate, has zero catastrophic forgetting (BWT = 0.0000) for all sequential learning tasks, and consistently shows positive forward transfer. Ablation and statistical significance analyses also validate the performance of adaptive quantum feature learning and continual adaptation under heterogeneous market conditions, regime-wise.
Oct 30, 2026

Implicit Assumptions About Tasks in Continual Learning

Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once. In practice, this is typically achieved by dividing a dataset into tasks and presenting them sequentially. Explanations of the resulting measurements take into account factors such as the similarity between segments, the rate at which the data changes and the order of presentation. Each of these factors can be defined in terms of the underlying data, the partition imposed on it, or the learner that encounters it. These levels do not necessarily coincide, and it is usually left implicit which level a reported quantity refers to. We separate these and identify which properties acquire a value at each level. In controlled teacher--student experiments, we demonstrate that partitioning the same underlying trajectory at different levels of granularity, changing the order of presentation, and varying the similarity structure of the underlying data all result in different measured outcomes. We review representative benchmarks to determine which of these properties are stated. Where the underlying data cannot be inspected, as in foundation models built on undisclosed pre-training corpora, its properties are inherited by the model's initial state, and the training applied on top of it can be described.
Oct 29, 2026

Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors

Continual adaptation requires deciding not only how to update a model, but whether to commit an update without exceeding a declared budget for changes to protected behavior. We introduce Certified Anchor-Based Adaptation (CABA), a candidate-agnostic post-update gate that reserves historical observations from candidate optimization, compares old and candidate policies on frozen representations, and selects the largest tested interpolation coefficient whose worst-anchor forward KL divergence remains within budget. The finite check requires neither action labels nor complete trajectories. We develop a theory-led certification framework that separates measured anchor retention from conditional off-anchor guarantees. Under explicit representation-coverage and Lipschitz assumptions, an accepted update satisfies a uniform behavioral-divergence bound on protected support. The analysis gives regularity bounds for affine softmax heads, probabilistic coverage and compression guarantees, interpolation monotonicity conditions, grid-resolution bounds, and trajectory-level and sequential-composition guarantees. In a controlled UCI Human Activity Recognition study used as a non-stationary sensor-policy proxy, CABA reduces mean forgetting from 1.01 percent for unconstrained adaptation to 0.00 percent at budget epsilon = 0.05, while reducing final average accuracy from 93.04 percent to 88.48 percent. The experiment illustrates a retention-plasticity trade-off and does not establish foundation-model or robotic performance. CABA provides an auditable retention check for candidate generators exposing comparable policy distributions and a declared update path, while deployment also requires separate evidence of current-task utility.
Oct 28, 2026

Episodic looking - using reinforcement learning to bias perception enhances few-shot and continual learning with protection from forgetting

There is a fundamental contradiction between the desire for models that can generalize, and models that can continuously adapt to recent input with changing statistics. These conditions, captured in few-shot and continual learning settings, can bias or disrupt learned representations. This harms generalization to a broader context, leaving the model unable to overcome input variance. This paper proposes a solution based on the Complementary Learning System architecture (CLS), in which a Short-Term Memory (STM) delegates generalization to a slow, statistical Long-Term Memory (LTM). Delegation is achieved by working in a space of robust, generalized perceptions produced by the LTM. With this separation, the STM can focus on memorizing recent input and avoiding interference between memories. We show that on an image classification task, the resulting CLS model is more resistant to forgetting in a domain-incremental continual learning setting than a baseline ResNet LTM, and generalizes more effectively in a few-shot setting than other continual learners. In the continual setting, overall accuracy is slightly worse than existing continual learning models, but with a different mix of performance characteristics. Results analysis suggests that the model is limited by the representations and representational plasticity of the LTM. In future work, we will seek to address this by replaying STM memories to the LTM.
Oct 28, 2026

Continual Adaptation Across Modalities: Learning and Forgetting in Unified Multimodal Models

Unified multimodal models (UMMs), which can process and generate diverse modalities within a single framework, have recently emerged as a powerful paradigm. However, when these models undergo continual learning on multiple tasks across different modalities, their learning and forgetting dynamics remain poorly understood. In this paper, we systematically investigate how architectural design and adaptation method shape intra-modal learning and cross-modal interference between the generation and understanding sides. Specifically, we report three findings. First, the severity of cross-modal interference decreases with the degree of modality-specific parameter isolation. Second, a within-model asymmetry: the generation side of a UMM is markedly more fragile than its understanding side. Third, what post-training adds is the first to be forgotten: purely post-training capabilities such as personalized generation collapse by 84% to 90%, while pretraining capabilities remain stable. Together, these results clarify how parameter isolation and post-training fragility shape UMMs' learning and forgetting dynamics, offering a starting point for developing continually evolving UMMs.
Oct 27, 2026

CAMR: Compatibility-Aware Memory Replay for Continual Learning in Large Language Models

Continual learning requires large language models to acquire new knowledge and capabilities while retaining what they have learned. Fine-tuning and replay support acquisition and retention, but deciding whether incoming examples need supervision and which historical examples to revisit remains a challenge. We propose Compatibility-Aware Memory Replay (CAMR), an adaptive framework that jointly controls current-example supervision and historical replay. CAMR combines compatibility checks with a learned memory gate to guide an online policy over three actions: learning incoming examples with general replay, jointly reinforcing compatible related examples, and skipping direct supervision of verified mastered duplicates. The policy learns from acquisition, retention, and training-cost feedback under a bounded per-arrival replay budget. We evaluate CAMR with Qwen3-8B-Base on continual factual updating and cross-task and cross-domain learning. On WikiBigEdit, CAMR consistently leads evaluated methods in Original Match from 3K to 100K facts, reaching 93.66% after just 3K facts and surpassing Full-history Replay (LoRA) after 100K facts. It also achieves the highest final scores on all four selected TRACE tasks and maintains or improves earlier-task performance relative to post-acquisition levels in a sequence spanning financial question answering, mathematical reasoning, code generation, and summarization.
Oct 27, 2026

ARISE: Authentic Reference-Informed Stability Enhancement for Continual Multimodal Forgery Detection

Multimodal forgery detection is commonly studied under a static assumption: training attacks are expected to approximate those encountered after deployment. This assumption becomes increasingly fragile as generators, editing systems, and multimodal large language models continually introduce new forgery mechanisms and forensic evidence. We formulate this problem as attack-incremental continual multimodal forgery detection, where the binary real/fake interface remains fixed while emerging attacks must be learned without forgetting previous ones. We introduce Fable-Bench, which organizes attack evolution through complementary joint-modality, text-side, and image-side protocols. We further propose ARISE (Authentic Reference-Informed Stability Enhancement), motivated by the open-ended forged class and the comparatively reusable geometry of authentic content. ARISE fits a real-only Gaussian mixture model to projected authentic replay representations as a compact historical reference. Meanwhile, the proposed Gaussian-Responsibility-Aware Stability Preservation (GRASP) derives a sample-adaptive anisotropic metric that strongly constrains historically stable representation directions while retaining plasticity elsewhere. Our Vulnerability-Aware Replay (VAR) further estimates stage-wise vulnerability from authentic-density degradation, forged-to-authentic boundary confusion, and authentic-mode occupancy drift, then assigns bounded replay emphasis to fragile stages. All adaptive signals are obtained from training-time replay statistics, while inference uses only the original multimodal backbone and binary classification head. Experiments across three attack-evolution protocols and multiple detector architectures demonstrate improved historical retention and final average performance over representative continual-learning baselines.
Oct 26, 2026

Rethinking Data Imbalance in Class Incremental Surgical Instrument Segmentation

In surgical instrument segmentation, the increasing variety of instruments over time poses a significant challenge for existing neural networks, as they are unable to effectively learn such incremental tasks and suffer from catastrophic forgetting. When learning new data, the model experiences a sharp performance drop on previously learned data. Although several continual learning methods have been proposed for incremental understanding tasks in surgical scenarios, the issue of data imbalance often leads to a strong bias in the segmentation head, resulting in poor performance. Data imbalance can occur in two forms: (i) class imbalance between new and old data, and (ii) class imbalance within the same time point of data. Such imbalances often cause the dominant classes to take over the training process of continual semantic segmentation (CSS). To address this issue, we propose SurgCSS, a novel plug-and-play CSS framework for surgical instrument segmentation under data imbalance. Specifically, we generate realistic surgical backgrounds through inpainting and blend instrument foregrounds with the generated backgrounds in a class-aware manner to balance the data distribution in various scenarios. We further propose the Class Desensitization Loss by employing contrastive learning to correct edge biases caused by data imbalance. Moreover, we dynamically fuse the weight parameters of the old and new models to achieve a better trade-off between the biased and unbiased model weights. To investigate the data imbalance problem in surgical scenarios, we construct a new benchmark for surgical instrument CSS by integrating datasets. Extensive experiments demonstrate the effectiveness of the proposed framework, achieving significant performance improvement against existing baselines.
Oct 26, 2026

Harness-Model Collaboration for Long-Horizon Continual Learning

Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persistent learning for rapid reuse. This limitation is especially important for Web agents that repeatedly execute related multi-step workflows. We propose HaMo, a Harness-Model collaborative framework that combines fast non-parametric experience accumulation with slow parametric adaptation. HaMo distills trajectories into strategy-level experience cards for immediate retrieval, while an experience-conditioned continual learning objective trains the model to interpret, ground, and execute retrieved strategies across changing contexts. A retrieval-coverage-based selection mechanism further identifies compact and complementary trajectories for parameter updates. Experiments show that HaMo outperforms harness-only and model-only adaptation under within-domain and cross-domain shifts, improving both retention and adaptation. These results highlight the importance of jointly preserving procedural experience and internalizing the competence to transfer and execute it across tasks.
Oct 25, 2026

Task Relevance-Driven Prompt Expansion for Federated Continual Learning

Federated continual learning (FCL) has attracted considerable interest by enabling local clients to continually acquire knowledge from new tasks. However, most FCL methods assume that the global server has prior knowledge of the arrival times and number of categories for new tasks, which is unrealistic in the real world. Furthermore, they neglect the importance of positive inter-task semantic relationships when learning new tasks and are significantly affected by irrelevant relationships from old tasks, thereby exacerbating catastrophic forgetting. To resolve the above challenges, we develop a novel Task Relevance-driven Prompt Expansion (TRPE) model. Specifically, to eliminate the reliance on prior knowledge of new tasks, we propose an out-of-distribution detector to identify the arrival of new tasks within local clients, along with a radius-adaptive DBSCAN to infer the quantity of categories in new tasks on the proxy server. Moreover, to explore positive inter-task relationships, we calculate the affinity between the original gradient for learning new task and its gradient orthogonal to the feature space of old tasks to evaluate semantic relevance between old and new tasks from a global perspective. Then, we use this global task relevance to determine the key-prompt pair for new tasks and identify highly related old tasks. After concatenating their prompts for training, we can leverage such positive inter-task relations to improve the continual learning of newly arriving tasks. To balance the learning of new tasks and the forgetting of old ones, a soft orthogonality constraint is applied to the local key and prompt gradients. Experiments spanning diverse datasets and backbones confirm the efficacy of our TRPE model.
Oct 25, 2026

Cross-User Adaptation for sEMG Gesture Recognition via Continual Learning

Prosthetic and assistive interfaces increasingly depend on decoding hand gestures from surface electromyography (sEMG). Because the signal is shaped by person-specific factors, the recurrent neural networks (RNNs) commonly used to model these temporal streams must adapt to new wearers and new gesture classes after deployment. Continual learning (CL) enables this adaptation without retraining from scratch, yet applying it to recurrent sEMG models is not straightforward. Standard recurrent training practices can destabilize learning, and which CL strategy holds up under realistic cross-user drift is unestablished. We evaluate three representative CL strategies under domain- and class-incremental drift on NinaPro DB1, and find experience replay to outperform elastic weight consolidation (EWC) and naive fine-tuning. It reaches 83.3% final accuracy for class-incremental drift while limiting forgetting to 1.8-5.8% accuracy drop, as against 16.2-28.5% for EWC and naive training. We further show these models must be trained on shuffled, independently-windowed segments. Streaming windows in temporal order collapses the network into predicting a single dominant gesture, while a shuffled, stateless regime trains stably. Finally, hand-crafted time-domain features raise per-task accuracy by up to about 40% over raw signals, but only replay preserves that gain under class-incremental drift.
Oct 23, 2026

Score-Preserving Continual Lasso under Task Shift

Continual learning (CL) aims to learn from sequential tasks while mitigating catastrophic forgetting when historical data are no longer accessible. We study continual learning for high-dimensional sparse linear regression, where ℓ1\ell_1 regularization creates a difficulty absent from continual ridge regression: that recursively reusing an ℓ1\ell_1-penalized estimator can propagate earlier shrinkage and accumulate regularization bias across tasks. We propose score-preserving continual Lasso (SP-CL), which separates sparse estimation from state transmission by preserving the historical squared-loss score. Under squared loss, its cumulative estimator exactly recovers a full-history Lasso minimizer. When task coefficients coincide, it inherits the full-history sparse rate. For related task-specific coefficients, SP-CL uses a regularized current-task correction that leaves the transmitted state unchanged and attains the offline source-assisted rate under an oracle related-task condition. We also derive Overall/BWT/FWT decompositions that distinguish historical information loss, task conflict, and current-task specialization, and validate the resulting regimes in simulation.
Oct 23, 2026

WiMoT: Replay-Free Continual Wi-Fi Sensing via Moment Transport

Continual Wi-Fi sensing must learn new rooms or users (plasticity) while keeping earlier ones (stability), yet sensing nodes often cannot retain channel state information (CSI) for privacy and storage reasons. We propose WiMoT (Wi-Fi Moment Transport), which stores the per-class feature mean and covariance of every earlier domain instead of samples. Stored statistics become stale when the representation changes, so WiMoT restricts the change to an affine map on a frozen feature basis and applies the same map to the statistics, which then stay valid without old samples. Supervised contrastive learning learns the new domain, a closed-form loss on the stored statistics keeps earlier classes separable, and a Gaussian discriminant classifier refitted from the transported statistics predicts without domain identity. On 3DO, WiMANS, and Widar3.0, WiMoT reaches average final accuracies of 94.02%, 89.61%, and 95.16% with at most 0.58 percentage points (pp) of forgetting. On 3DO and Widar3.0 it is 3.77 and 13.11 pp ahead of the strongest of 21 baselines, which uses replay; on WiMANS it matches the strongest replay baseline in accuracy while reducing forgetting from 2.78 to 0.00 pp. Rank-32 covariance factors shrink the moment memory to 6.4% at a cost of at most 0.49 pp.
Oct 22, 2026

HERD: Harness-Evolving Recursive Distillation for Continual Learning

Continual learning requires a model to keep acquiring new skills and knowledge without compromising its existing capabilities. Parametric methods suffer from catastrophic forgetting and loss of plasticity. Non-parametric methods, such as prompts, skills, and harnesses, leverage in-context learning but are limited by context length and lossy plain-text compression. To effectively combine their complementary strengths, we propose HERD (Harness-Evolving Recursive Distillation), a hybrid continual learning framework that learns efficiently in the harness and internalizes experience into cumulative capabilities via distillation. On the harness side, HERD continually refines its skills to capture reusable patterns, while retaining high-residual examples that the skills fail to capture in a bounded memory. On the parameter side, HERD performs drift-constrained distillation with dual anchors, substantially reducing forgetting over long recursive runs. On the 25-stage task stream of TRACE+17, under fixed memory and compute budgets, HERD matches the strongest parametric baseline in new-task acquisition while exhibiting the least forgetting and the strongest retention of general capabilities.
Oct 19, 2026

Language Guidance for Supervised Vision Training: An Empirical Study of Generalization

Deep neural networks have achieved remarkable success on vision benchmarks, yet they continue to struggle with many generalization challenges. Supervised vision training relies on one-hot labels, which provide limited information about semantic structure and shared attributes between classes. This limited supervision can leave visual representations vulnerable to distribution shifts, spurious correlations, texture bias, adversarial perturbations, and forgetting in sequential learning settings. We study whether pretrained language models can serve as lightweight auxiliary supervision for vision training without requiring paired image-text data, prompt engineering, or contrastive objectives. Specifically, we evaluate two forms of language guidance, Explicit Language Guidance (ExLG) and Implicit Language Guidance (ImLG). We conduct a comprehensive evaluation across six generalization regimes, including in-distribution, out-of-distribution generalization, shortcut and spurious correlation resistance, texture and shape bias, adversarial robustness, and continual learning. Our analyses show that the two mechanisms have complementary strengths, with explicit guidance consistently benefiting in-distribution, low-data performance, and continual learning retention, while implicit guidance is often more useful in shortcut-sensitive settings and under stronger adversarial perturbations. Importantly, both are lightweight and add minimal parameters and training overhead. The analyses characterize when language-derived structure helps supervised vision training and provides a practical roadmap for using off-the-shelf pretrained models from another modality as auxiliary supervision.
Oct 19, 2026

Out-of-Distribution Detection in Continual Learning

Out-of-distribution detection in continual learning (OOD-CL) is highly challenging, as it requires (i) learning a sequence of tasks without catastrophic forgetting, and (ii) identifying unknown samples (OOD) without access to known (in-distribution (ID)) data from past tasks, where standard confidence-based OOD scores tend to degrade. Existing methods largely rely on a rehearsal buffer of past data or assume closed-world settings, limiting their scalability and reliability in real-world scenarios. In this paper, we propose a novel OOD detection framework for rehearsal-free continual learning, inspired by Kolmogorov-Arnold Networks (KAN), which mitigate catastrophic forgetting via their inherent local neuroplasticity. To better leverage KAN in OOD-CL, we introduce a task-adaptive classifier architecture, TA-KAN, which mitigates recency bias and enhances ID--OOD separability through task-specific control of activation locality. Furthermore, we propose a geometry-guided OOD score that complements TA-KAN classifier confidence without relying on past ID data. Our method significantly improves OOD detection while maintaining strong ID classification performance, achieving state-of-the-art results in OOD-CL.
Oct 17, 2026

An Impossibility Result for ETF Target Geometry, and an Equinorm Remedy for Imbalanced Analytic Continual Learning

Analytic continual learning (ACL) methods such as ACIL and GACL fit a ridge-regression classifier head on frozen features via the Sherman-Morrison-Woodbury identity, achieving exemplar-free, exact updates. A separate line of work, Progressive Neural Collapse (ProNC), shows standard continual classifiers benefit from a progressively expanding Simplex Equiangular Tight Frame (ETF) target. It is natural to ask whether fusing the two ideas, exact analytic updates and ETF targets, would yield a better closed-form continual learner. We show this is not the case as the fusion turns out to be identical to plain one-hot ACIL. Further, Simplex ETFs are not nested across class counts, so the literal "progressively expand the ETF" construction stops yielding an ETF as new tasks arrive, and it introduces catastrophic forgetting (4×4\times that of a classic ACIL head). We therefore separate an ETF's two defining properties, equiangularity and equinormality, and apply each on its own to the classifier weights rather than the targets, where the invariance above does not hold. Equinorm post-processing of the fitted weights recovers both tail-class and overall average accuracy across the long-tailed regime from 5:1 to 100:1 imbalance (e.g. +32.0 tail-accuracy points and +16.0 average-accuracy points at 100:1 on CIFAR-100/ViT), transferring in sign across two backbones and two datasets, at a mild cost of 5.4 average-accuracy points on CIFAR-100/ViT on near-balanced streams (below ≈3:1\approx 3{:}1). Equiangular geometry, by contrast, is exactly inert on the target side but actively harmful on the weight side, usually losing to plain one-hot. Hence, the generally useful part of Neural Collapse geometry in Analytic Continual Learning is equinorm post-processing of the weights, becoming more useful as class imbalance grows; and equiangularity is at best a no-op and induces catastrophic forgetting at worst.
Oct 15, 2026

Reliable Knowledge Acquisition for Continual Learning Agents

As agents powered by foundation models move into open-ended environments, continual learning from experience becomes essential. For agents built on models with fixed parameters, this learning requires reusing prior task experience in context to improve performance and efficiency on future tasks. Existing memory and experience-learning systems typically focus on either retained facts or procedures, and lack a mechanism for establishing the reliability of claims extracted from the ongoing task stream. Indeed, we find that approximately 12--33% of entries produced by representative systems harm future task performance when reused. To address these limitations, we propose RIKA (Reliable Knowledge Acquisition), which combines hierarchical extraction of factual, conceptual, procedural, and metacognitive knowledge with Evidence-based Knowledge Admission, which uses source evidence and subsequent experience to govern which claims enter the task agent's context, without additional validation tasks. Across six task streams from Continual Learning Bench and four model backbones, RIKA achieves the highest aggregate score on every backbone.
Oct 13, 2026

Overcoming Catastrophic Forgetting: Continual Learning for Radar Waveform Classification

Automated radar waveform recognition classifies the waveform and modulation type of a received signal. As new waveform variants appear over time, a deployed classifier must learn them without retraining from scratch. Catastrophic Forgetting occurs when learning new waveforms overwrites prior knowledge. Continual Learning (CL) methods tackle this challenge, but prior radar studies only evaluate a few methods on narrow benchmarks. Practitioners lack evidence on which method to deploy or which mechanisms are effective. This work presents the first large-scale benchmark of continual learning for radar waveform recognition. Eighteen CL methods are evaluated on a sequential ten-task problem, drawn from four public datasets spanning 54 waveforms, under task- and class-incremental (TIL, CIL) settings and single- and multi-epoch regimes. Methods that retain data from old tasks lead both TIL and CIL settings. Plain replay alone closes 77-88% of the gap between the lower and upper practical limits under TIL, but only 46-55% under CIL. The internal mechanisms of the leading methods are ablated and statistically tested to identify effective mechanisms. Each ablation is paired against its full method over n=6 training seeds, topped up to n=12 when inconclusive, and p-values are Holm-Bonferroni corrected within each method's family. Ablation results show that several mechanisms confer smaller but statistically significant gains. Combining these mechanisms improves the leading F1 score by 3.4-5.5% and 2.7-4.9% under TIL and CIL, respectively, and the combined models exceed every benchmarked method in both settings for all SNRs. These results give researchers of radar waveform classification systems a mechanism-level basis for design.