Continual Learning

Ask about this topic

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

CardsList

305 papers36 papers in the last four weeks, up 89% on the four weeks before. 0.2% of all new papers.

Jun 4, 2026

Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning

Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning. In this work, we investigate an alternative perspective: that forgetting may arise not from complete destruction of task representations but from a loss of accessibility to preserved information. We introduce a three-level framework separating knowledge storage, representation, and accessibility, and evaluate each component through a series of continual-learning experiments on sequential CIFAR-100 classification using ResNet-18. Our analysis combines checkpoint persistence, linear probing, representation geometry, classifier-reset recovery, and layer-wise recoverability experiments. We observe complete behavioral forgetting of earlier tasks, with task accuracy collapsing from 54.8% to 0%, while linear probe performance retains approximately 76% of the original representational information. Furthermore, retraining only the final classifier restores 75.7% of the original task performance without modifying the backbone network. Layer-wise analysis reveals that early and intermediate layers preserve highly recoverable task information despite severe degradation at later stages. Projection-energy and principal-angle analyses indicate that retained knowledge persists as distributed high-dimensional representations rather than through preservation of a small dominant subspace. These findings suggest that catastrophic forgetting is better characterized as an accessibility failure than complete representational erasure, and that substantial task-relevant information remains embedded within neural representations even after functional forgetting has occurred.

Ayushman Trivedi, Bhavika Melwani

Independent Researchers

Continual LearningCatastrophic Forgetting
AskPDF
Jun 4, 2026

Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments

Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it. We introduce Continual Learning Bench (CL-Bench), the first difficult, expert-validated benchmark designed to measure whether LLM-based systems genuinely improve with experience. CL-Bench spans six diverse domains (software engineering, signal processing, disease outbreak forecasting, database querying, strategic game-playing, and demand forecasting), each validated by domain experts and designed so that tasks share a learnable latent structure (codebase layout, disease outbreak dynamics, opponent strategies) that a stateful system can discover online but a stateless one cannot. We evaluate frontier models across several agent architectures, from naive in-context learning (ICL) to dedicated memory systems, introducing a gain metric to isolate learning from prior capabilities. We find that these systems leave headroom for improved continual learning: agents frequently overfit to immediate observations or fail to reuse knowledge across instances, and dedicated memory systems do not fix this -- in fact, naive ICL outperforms systems dedicated to memory management. CL-Bench is the first benchmark to evaluate continual learning across diverse real-world domains with expert-validated tasks and isolate online learning from underlying model capability, showing a need for better continual learning systems.

Parth Asawa, Christopher M. Glaze, Gabriel Orlanski +7

UC Berkeley · Snorkel AI · University of Wisconsin-Madison +1

Continual Learning for LLM AgentsContinual Learning for LLMsContinual LearningOnline Continual LearningMemory-Augmented Language Model Agents
AskPDF
Jun 4, 2026

CLaaS: Continual learning as a service for sample efficient online learning

Deployed large language model agents must adapt to distribution shift in dynamic environments. Ideally, adaptation can be performed from accumulated agent experiences and retain prior capabilities while transferring to future tasks. However, agent actions and environmental transitions can only be sampled once per scenario, as real-world environments cannot be trivially reset. To this end, we investigate an experiential and online continual learning setting in which agents learn from a stream of scenarios. We propose continual learning as-a-service (CLaaS), a system which enables agents to improve during deployment, abstracted behind a chat API. To increase sample efficiency, CLaaS stores rollouts in an experience replay buffer for gradient reuse during asynchronous training. We evaluate CLaaS on an adversarial task, demonstrating that parametric updates lead to superior forward transfer and less forgetting than in-context learning, with replay being a critical choice for sample efficiency.

Kion Fallah, Silen Naihin, Barak Widawsky +1

1Resolute Labs · 2South Park Commons · 3Incept Labs

Continual Learning for LLM AgentsContinual LearningReplay-Based Continual LearningOnline Continual LearningData-Efficient Learning
AskPDF
Jun 3, 2026

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs). While prior work has predominantly focused on single-iteration transfer, we discover that under multi-iteration experience learning, existing methods suffer from a progressive capability collapse rather than compounding improvement. We systematically examine this failure through three vital dimensions of experience internalization: (1) Experience Granularity: We find that principle-level experience is more durable than instance-level experience, as it effectively abstracts transferable strategies away from trajectory-specific details. (2) Experience Injection Pattern: Our analysis reveals that step-wise injection significantly outperforms global injection by aligning experience with intermediate decision states, a property that is critical for long-horizon tool use. (3) Internalization Regime: We demonstrate that off-policy context-distillation on high-quality teacher trajectories provides a substantially more stable training signal than on-policy context-distillation, which is inherently limited by local corrections on student-induced flawed states. Together, these insights yield a simple yet robust recipe for stable and sustainable experience internalization, providing concrete guidance for engineering self-evolving and continually learning LLMs.

Jingwen Chen, Wenkai Yang, Shengda Fan +7

1Gaoling School of Artificial Intelligence, Renmin University of China · School of Software, Beihang University · 3Meituan

Continual Learning for LLM AgentsContinual Learning for LLMsContinual LearningContext Distillation
AskPDF
Jun 2, 2026

Re-Evaluating Continual Learning with Few-Shot Adaptation

Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks. The standard measure of stability (i.e., forgetting) is the 0-shot performance of a model on previously learned tasks, and plasticity, the performance on the most recently learned task. However, 0-shot evaluation does not fully measure a model or method's ability to retain learned information or adapt quickly to new information, as it requires perfect recall across multiple tasks. In this paper, we propose few-shot evaluation as a more comprehensive assessment of the stability and plasticity of a continual learning system. We conduct a fine-grained assessment on task sequences for continual image classification and find that this paradigm produces novel insights into the performance of popular continual learning strategies. Through few-shot evaluation with a novel metric -- per-shot plasticity -- we show that adding `foresight' to continual learning methods via the meta-learning of a short sequence of future tasks induces learning-to-learn behavior over the task sequence.

Amogh Inamdar, Matthew So, Vici Milenia +1

Department of Computer Science Columbia University

Continual Learning
AskPDF
Jun 2, 2026

SkillHarness: Harnessing Safe Skills for Computer-Use Agents

Computer-Use Agents (CUAs) are increasingly deployed in dynamic interactive environments, creating a growing need for continual skill learning during interaction. Recent approaches address this challenge by learning reusable skills from successful trajectories. However, these skill learning methods largely assume static and safe environments, overlooking risks from adversarial interactions (e.g., prompt injections) and environmental dynamics (e.g., pop-ups). In dynamic settings, such assumptions can lead to risky skill learning and brittle execution, undermining the reliability of CUAs. This raises the question: how can CUAs learn and use skills safely in dynamic environments? To address this problem, we propose SkillHarness, a framework for safe skill harnessing in dynamic environments. SkillHarness moves beyond static skill abstractions by modeling skill learning and utilization as a safety-constrained interaction process. Specifically, we introduce the skill boundary that leverages multi-source supervision signals to identify safe skills from interaction trajectories, and construct self-improving safety constraints throughout the skill lifecycle. In addition, SkillHarness introduces selective skill reuse, where tasks are guided to decompose according to context and completed through the selective activation of skill subsets. Our experiments demonstrate that SkillHarness significantly reduces the unsafe rate of learned skills by 57.1% and consistently improves execution stability under dynamic environmental changes, outperforming existing baselines.

Yurun Chen, Biao Yi, Keting Yin +1

Zhejiang University

Computer-Use AgentsContinual LearningAgent Skill Learning
AskPDF
Jun 1, 2026

Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys

Catastrophic forgetting is often framed as a representational problem: after sequential training, a model appears to lose the features that supported performance on earlier tasks. We challenge the stronger form of this view. Across controlled continual-learning settings, we find that a significant portion of apparent forgetting can be attributed to interface drift between internal stages rather than permanent erasure of task-relevant computation. We study this phenomenon through a stitched evaluation protocol that combines early computation from a post-update network with late computation from its predecessor, optionally mediated by a compact, task-specific transport key. We describe transport keys at a systems level as compact interface-alignment operators estimated from a small set of paired anchor activations and evaluated through model stitching. On split CIFAR-100 with a ResNet-style network, transport keys recover most of the original Task A performance after sequential training on Task B. On a compact vision transformer, we observe a similar recovery pattern. These results suggest that continual learning may require better mechanisms for indexing and re-accessing latent computations, not only methods that prevent weight change.

Archie Chaudhury

Axionic Labs

Continual LearningRepresentation AlignmentCatastrophic Forgetting
AskPDF
Jun 1, 2026

G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs

LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning. While effective on individual downstream tasks, we observe severe catastrophic forgetting when such models are sequentially fine-tuned on streaming tasks. Although parameter-efficient fine-tuning alleviates forgetting to some extent, it remains insufficient to resolve task interference and ineffective knowledge transfer. In this work, we study graph continual learning for LLM-as-Aligner models on TAGs, with the goal of mitigating interference while promoting positive transfer across tasks. This setting introduces two fundamental challenges: (1) heterogeneous downstream tasks induce shifting optimization objectives, hindering unified fine-tuning; and (2) graph and text encoders exhibit different sensitivities to adaptation, making uncoordinated updates prone to misalignment. To address these challenges, we propose G2LoRA, a continual learning framework for TAGs. G2LoRA unifies node-, link-, and graph-level tasks under a single graph--text alignment objective, and enables consistent optimization across domain/class/task incremental modes. To reduce task interference while encouraging positive transfer, G2LoRA performs category-aware gradient projection in structured subspaces, resolving conflicting updates and enabling conditional backward transfer to balance forward and backward knowledge flow. To further prevent cross-modal drift, G2LoRA introduces gradient magnitude modulation to coordinate update rates between graph and text encoders. Extensive experiments on benchmark datasets demonstrate that G2LoRA consistently outperforms strong baselines across different backbone architectures, achieving superior continual performance and transferability.

Yuhan Wang, Yibo Ding, Yutong Ye +4

School of Computer Science and Engineering, Beihang University Beijing, China · Department of Statistics, Columbia University New York, NY, USA · College of Computer Science, Beijing University of Technology Beijing, China

Continual LearningLow-Rank AdaptationText-Attributed Graph LearningGradient ProjectionTask-Free Continual Learning
AskPDF
Jun 1, 2026

Continual Learning as a Multiphase Moving-Boundary Problem

Continual learning struggles to balance retaining past knowledge with absorbing new tasks. Stefan-CL elegantly resolves this stability-plasticity dilemma through the physics of melting. It frames consolidated knowledge as a protected "solid" and unused capacity as an adaptable "liquid." As the network learns, this boundary expands, governed by a "latent heat" tuning dial. By mathematically freezing the learned interior, Stefan-CL cuts forgetting to near zero, matching memory-heavy baselines without storing raw data, forging a beautiful, physics-grounded path for AI.

Snigdha Chandan Khilar

Independent Researcher

Continual LearningCatastrophic Forgetting
AskPDF
Jun 1, 2026

EvoBrain: Continual Learning of EEG Foundation Models Across Heterogeneous BCI Tasks

Electroencephalography (EEG) is the cornerstone of non-invasive brain-computer interfaces (BCIs), yet conventional decoding relies on fragmented, task-specific architectures that severely limit cross-task scalability. While EEG foundation models pre-trained on massive corpora promise universal brain decoding, current post-training depends on task-isolated fine-tuning. This static paradigm restricts knowledge transfer across heterogeneous tasks, hinders model scalability, and incurs computational and storage overheads that scale linearly with task count. To overcome these bottlenecks, we formulate downstream adaptation as a cross-task continual learning problem and propose EvoBrain, a dynamic, task-aware continual learning framework for unified EEG decoding. EvoBrain addresses the plasticity-stability trade-off via two complementary components: (1) Neuro-Spectral Task Normalization (NSN) aligns incoming tasks with historical statistics while recalibrating spectral responses to handle distributional and neuro-spectral shifts; and (2) Response-Affinity Distillation (RAD), combined with time-dependent replay, preserves old-task response geometry and promotes selective knowledge transfer between spectrally compatible tasks, effectively mitigating forgetting. Extensive evaluations across six distinct BCI tasks demonstrate that EvoBrain consistently surpasses state-of-the-art methods across diverse foundation backbones, optimally balancing plasticity and stability. To our knowledge, this work pioneers cross-task continual learning in the EEG domain, advancing the realization of a unified, one-for-all brain decoding system.

Yangxuan Zhou, Sha Zhao, Jiquan Wang +2

State Key Laboratory of Brain-machine Intelligence and College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China · MOE Frontier Science Center for Brain Science and Brain-Machine Integration, Zhejiang University, Hangzhou, Zhejiang, China

Brain-Computer InterfacesEEG DecodingContinual LearningReplay-Based Continual LearningEEG Foundation Models
AskPDF
May 30, 2026

Task diversity produces systematic transfer but inhibits continual reinforcement learning

Continual reinforcement learning (RL) aims to produce agents that never stop adapting to new tasks. A key question is how this interacts with the diversity of tasks an agent experiences. Prior work has shown that training on many diverse tasks leads to agents with strong zero-shot and in-context adaptation. However, this work evaluated agents after they'd stopped learning, i.e. with frozen weights. How task diversity affects an agent's ability to continue learning over a sequence of distribution shifts remains unclear. We introduce Banyan, a GPU-accelerated continual RL domain where one can parametrically control three independent axes that define a task: the map layouts an agent must navigate, the objects it must interact with, and the hierarchical structures of sub-goal dependencies. We find that increasing diversity along each axis induces systematic transfer -- that is, agents begin training on a new task distribution near the performance attained on the previous one, even when the shift changes the structure of the optimal policy. While increasing diversity improves systematic transfer, we find that too much diversity inhibits a learner's ability to continue adapting to new task distributions. As diversity increases, learners plateau in the success rate they achieve on new tasks, yet continue improving on old tasks -- even without further exposure to them. We find this phenomenon manifests across continual learning algorithms, memory architectures, architecture sizes, and in Kinetix -- a physics-based control domain. We release Banyan as a domain for running controlled experiments that study continual RL in the many-tasks regime. Code is available at https://github.com/nhshah15/banyan.

Purab Seth, Neil Shah, Ishaan Sinha +4

Harvard College · University of Washington · Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University +1

Transfer LearningReinforcement LearningContinual LearningRL BenchmarksContinual RLGeneralization in RL+1
AskPDF
May 30, 2026

SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition

Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings. In these settings, data arrive sequentially and must be processed in a single pass without simultaneously revisiting past observations. Standard architectures, including recurrent neural networks and transformers, are constrained by either truncated backpropagation through time horizon or explicit input window length for long range credit assignment. To address these limitations, we propose SHARP (Sleep-based Hierarchical Accelerated Replay), a framework that decomposes temporal learning into two complementary components: a memory module that accumulates a structured history of past inputs, and a pattern-recognition module that operates over this memory. This separation enables resource- and compute-efficient adaptation to non-stationary dynamics by eliminating the need for backpropagation through time across many steps for long-range credit assignment. Inspired by the accelerated replay observed in rodents during slow-wave sleep, SHARP incorporates offline (sleep) phases in which temporally structured memory traces are replayed in an accelerated form and integrated into higher-level memory representations, improving long-range context retention. Through controlled simulations and ablation studies, we characterize the key properties of the proposed framework. In benchmark datasets such as text8 and PG-19, we demonstrate that SHARP improves over recurrent baselines by retaining next-token predictive performance on previously seen data while continuing to learn from the current stream and generalizing to future unseen data. These gains are enabled by its hierarchical structure, which yields an exponentially increasing effective temporal context with only linear-time computational cost.

Jayanta Dey, Shikhar Srivastava, Itamar Lerner +2

University of Texas at San Antonio, USA · University of Rochester, USA

Memory-Augmented Neural NetworksContinual LearningLong-Context ModelingReplay-Based Continual LearningLanguage ModelingOnline Continual Learning+1
AskPDF
May 29, 2026

Regime-Adaptive Continual Learning for Portfolio Management

Financial markets are inherently non-stationary, exhibiting frequent regime shifts and structural changes that render traditional Portfolio Management (PM) approaches ineffective. Existing remedies, such as rolling-window retraining and naive online fine-tuning, are hindered by high computational costs and insufficient knowledge utilization, respectively, resulting in low returns and limited adaptability. Continual learning (CL) offers a promising paradigm by enabling trading agents to accumulate and transfer knowledge across sequential tasks. In this paper, we propose Regime-aware Continual Adaptive Portfolio management (ReCAP), a novel framework that integrates CL into PM to address the challenges of dynamic financial environments. ReCAP employs an adaptive regime detection module to segment historical market data into variable-length regimes, enabling regime-specific learning of policy vectors and the construction of a policy library. During continual trading, a regime-gate module adaptively combines policy vectors from the library based on the current market state, facilitating rapid adaptation to newly detected regimes. Only the regime-gate and the current regime's policy vector are continually updated to preserve useful knowledge effectively. Extensive experiments on five real-world datasets demonstrate that ReCAP consistently outperforms popular baselines, achieving superior returns in long-term investment horizons and rapid adaptation to regime shifts.

Chaofan Pan, Lingfei Ren, Linbo Xiong +3

Southwestern University of Finance and Economics · Shanxi University

Continual LearningPortfolio OptimizationFinancial Time Series
AskPDF
May 28, 2026

Active Continual Learning with Metaplastic Binary Bayesian Neural Networks

Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic uncertainty and freezing plasticity. We propose BiMU, derived from a bounded-memory variational objective that balances stability, plasticity, and forgetting. BiMU combines a data term with controlled relaxation toward the prior and an uncertainty-dependent step size that prevents saturation and sustains informative uncertainty. This non-degenerate posterior enables fully online, buffer-free active querying via Monte Carlo disagreement, reducing label queries and backpropagation updates under imbalance. BiMU sustains learning and strong OOD detection on 1000-tasks Permuted-MNIST, and on OpenLORIS-Object achieves up to 32×\times label/update savings at matched accuracy under class imbalance and feature compression.

Kellian Cottart, Théo Ballet, Djohan Bonnet +1

Université Paris-Saclay, CNRS, Centre de Nanosciences et de Nanotechnologies, Palaiseau, France · Forschungszentrum Jülich, Germany

Bayesian Neural NetworksBinary Neural NetworksContinual LearningActive LearningOnline Continual LearningIncremental Learning+2
AskPDF
May 27, 2026

TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints

As machine learning(ML) systems evolve to continual adaptation, each re-training cycle uses compute, annotation, and energy. We introduce TIMEGATE, a policy layer managing adaptation by budgeting time, labeling, training, and evaluation. TIMEGATE emits a metric-availability signal M for partial vs. full-evaluation decisions. We validate: (i) labeling outperforms training by 2.3x on Adult tabular; (ii) it transfers to LLaMA-3.1-8B + QLoRA on SST-2 (accuracy 0.80 to 0.96; M =1 in 35/36 runs); (iii) M is informative, 28-cell sensitivity shows M drops to 0.81 at tight thresholds; (iv) 100-cycle simulation achieves 66% evaluation-compute savings with no silent mis-promotions; (v) 10%-slice evaluation on LLaMA uses 89% less wall-clock and energy on a single H200 (ratios agree to 0.2%).

Abhijit Chakraborty, Suddhasvatta Das, Yash Shah +2

School of Computing and Augmented Intelligence, Arizona State University, Tempe, USA

Energy-Efficient MLContinual Learning
AskPDF
May 27, 2026

Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning

Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors (AA and BB), creating a composite update to the full weight matrix through their interaction. To prevent catastrophic forgetting, this update should remain orthogonal to the task-specific subspace that contains previously learned knowledge. However, we identify that this composite update systematically violates this orthogonality, reintroducing interference and undermining stability. Furthermore, naively enforcing this orthogonality compromises plasticity, disrupting the delicate stability-plasticity trade-off. To resolve these issues, we propose Janus-LoRA, a framework that restores this balance through two novel components. Specifically, we first introduce Gradient Rectification, a closed-form solution that mathematically decouples LoRA's factor updates, enforcing orthogonality against the historical knowledge subspace identified by an efficient Online Estimation. Next, to enhance plasticity, we introduce a Decoupled Margin Loss that promotes feature-level separation by pushing new feature representations away from old ones, thus creating distinct, low-interference regions for new learning. Comprehensive experiments on challenging benchmarks demonstrate that by harmonizing parameter-level orthogonality with feature-level separation, Janus-LoRA achieves a superior balance and establishes new state-of-the-art performance.

Cheng Chen, Pengpeng Zeng, Yuyu Guo +3

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China · School of Computer Science and Technology, Tongji University, Shanghai, China · Independent Researcher +1

Stability-Plasticity DilemmaContinual LearningLow-Rank AdaptationParameter-Efficient Fine-TuningContinual LoRA
AskPDF
May 27, 2026

Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments

Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences and adapt their navigation behavior toward safe and efficient trajectories. Existing approaches either rely on handcrafted proprioceptive traversability scores, limiting robot-agnosticism, or cluster prior data, preventing online learning. Moreover, many continual learning methods incur substantial memory and computational costs, hindering onboard deployment. We introduce COTRATE, an online learning framework for continuous traversability estimation from multimodal, unlabeled robot experience. Our method first infers robust traversability scores using a robot-agnostic, learning-based online terrain assessment module operating on proprioceptiveand inertial signals. These scores then supervise a visual traversability network through a novel alignment loss that associates visual embeddings with online terrain assessments. To mitigate forgetting during continual learning with minimal overhead, we propose a diversity-aware feature selection strategythat preserves performance using a compact replay memory. We further show that the learned traversability representation supports knowledge transfer across different robot platforms with different locomotion kinematics. We evaluate COTRATE on a dataset of ≈\approx 50,000 images collected with two robotic platforms across 11 outdoor terrains, and benchmark it on navigation tasks in three representative outdoor environments. We make the dataset, code, and trained models publicly available.

Julia Hindel, Simon Bultmann, Houman Masnavi +2

Department of Computer Science, University of Freiburg, Germany.

Continual Robot LearningRobot Traversability EstimationRobot NavigationContinual LearningRobotic Perception
AskPDF
May 27, 2026

CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras

Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, both on-device processing and learning are essential for privacy and low-latency adaptation. Event cameras address the efficiency of visual sensing with sparse, asynchronous output that is naturally compatible with neuromorphic processing. Yet no prior system has deployed a continual on-device learning pipeline for event-based action recognition using neuromorphic hardware. We present CLANE, Continual Learning of Actions on Neuromorphic Hardware from Event Cameras, deployed end-to-end on Intel Loihi 2. CLANE combines a spiking 2D CNN for spatiotemporal feature extraction with CLP-SNN as its on-chip learning head, extended to action clips via a Temporal Aggregation Layer and a fixed-point Normalization Layer, both novel Loihi 2 modules. On THU E-ACT-50, a 50-class dataset captured under real-world conditions, CLANE achieves 70.4% accuracy in a continual learning task while delivering more than 100x energy reduction and 16x lower latency over a sequential CNN+GRU+CLP edge GPU baseline, validated through iso-algorithm cross-platform benchmarking across three evaluation levels.

Elvin Hajizada, Michael Neumeier, Edward Paxon Frady +4

Institute of Informatics, University of Munich (LMU), Munich, Germany · fortiss GmbH, Neuromorphic Computing, Munich, Germany · Technical University of Munich, TUM School of CIT, Munich, Germany +5

Event-Based VisionContinual LearningSpiking Neural NetworksNeuromorphic Computing
AskPDF
May 26, 2026

COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection

Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continually evolve, and existing OVD models still struggle with newly emerging concepts, while repeated full retraining is prohibitively expensive. To this end, we introduce a new task setting, termed Continual OVD with Novel Concept Injection (COVD), where models sequentially learn incoming novel concept groups while preserving prior concepts and original open-vocabulary knowledge, along with a new benchmark, Novel-114. Our key observation is that pretrained visual encoders often already perceive and represent many novel concepts, and the main bottleneck lies in the lack of stable semantic alignment between visual representations and textual concepts. Based on this, we propose NoIn-Det, an efficient continual injection framework without additional parameters. NoIn-Det freezes the visual encoder, preserves the text representation space using only texts of common concepts and previously injected concepts, and injects novel concepts by updating only a small subset of text-branch parameters beneficial to novel concept learning. Extensive experiments show that NoIn-Det effectively learns novel concepts, preserves old knowledge, and consistently outperforms existing continual learning methods for VLMs without introducing additional parameters.Novel-114 and the code will be released.

Yupeng Zhang, Ruize Han, Yuzhong Feng +3

Tianjin University. · Shenzhen University of Advanced Technology.

Open-Vocabulary Object DetectionVLM AdaptationContinual LearningContinual Object Detection
AskPDF
May 26, 2026

Energy-Structured Low-Rank Adaptation for Continual Learning

While orthogonal subspace methods try to mitigate task interference in Continual Learning (CL), they often suffer from energy diffusion across the basis, hindering knowledge compaction and exhausting capacity for future tasks. We observe that output feature drift induced by parameter updates is inherently low-rank, and theoretically prove that preserving parameters along the principal directions of this drift minimizes the output reconstruction error. Motivated by this, we propose Energy-Concentrated and Energy-Ordered Low-Rank Adaptation (E2^2-LoRA). By explicitly ordering and concentrating knowledge into leading ranks, E2^2-LoRA frees capacity for subsequent tasks. Furthermore, we design a dynamic rank allocation strategy to balance stability and plasticity by jointly optimizing energy retention and model plasticity. Extensive experiments across multiple benchmarks demonstrate that E2^2-LoRA achieves state-of-the-art performance. Code is available at https://github.com/kiddo127/E2-LoRA.

Longhua Li, Lei Qi, Qi Tian +1

School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China · Huawei Technologies, Shenzhen, China

Continual LearningLow-Rank AdaptationAdaptive Rank AllocationParameter-Efficient Fine-TuningContinual LoRAAdapter-Based Continual Learning
AskPDF
May 26, 2026

Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift

Continual Learning (CL) is a practical paradigm to utilize power of deep pre-trained neural networks, but which pre-trained model has a better ability to balance ``Plasticity-Stability", deserving to be chosen? The logit shift serves as a natural proxy because it represents the logit shift in CL scenarios. However, obtaining the logit shift requires huge computational cost, which hinders large-scale model selection. Existing theoretical analyses fail to offer an efficient alternative because of the assumption of uniform hidden layer widths, which ignores the structural heterogeneity (variable width and depth) of real-world architectures. This raises a critical question: what theoretically relationship can be identified between heterogeneous architecture and logit shift on prior tasks (that the model has been trained on)? To answer the question, we decouple logit shift into architecture dependency and data dependency to establish our framework, which reveals that the combination of two dependency, defined as Architecture-driven Shift (ADS), that can capture the logit shift tendency well computable with few data samples. Specifically, for a well-optimized model on prior tasks, higher ADS is associated with a larger logit shift after training on the current task, which derived based on three mechanistic components: (1) spectral norm scaling of weight matrix gradients with layer width, (2) the optimization path length of the new task, and (3) the asymptotic task conflict in wide networks. Extensive empirical results across more than 175 diverse architectures demonstrate a strong monotonic correlation (the weakest Spearman's rs=0.731r_s=0.731) between ADS and logit shift. Practically, we demonstrate that ADS can serve as a lightweight proxy of the expected calibration error, which is a widely used metric for reliable CL model selection, on three datasets across six scenarios.

Zhong Ye, Yu Hu, Ruilin Tang

School of Computer Science and Technology Guangdong University of Technology Guangzhou, China · School of Computer Science and Engineering2026 South China University of Technology Guangzhou, China

Continual LearningNeural Network Training Dynamics
AskPDF
May 24, 2026

Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation

Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models. Olfactory navigation is a highly dynamic and non-stationary task that benefits from real-time continual learning. We introduce an adaptive framework called Grow-Prune-Freeze (GPF) networks that enable an agent to continually learn through growing, pruning, and freezing early layers of its policy in response to world complexity. Grounding GPFs in non-linear random matrix theory, we show that the work of Pennington & Worth (2017) can be extended from single hidden layers to n-layer continual-learning models, and that eigenvalue composition of network weights is preserved as successive layers are added. We show that GPFs based on Expected SARSA achieve a 94% success rate on turbulent plume navigation - a partially observable, non-stationary task representative of the "big world" challenges that motivate adaptive learning in robotics - and provide supporting methodology for applying GPFs in other world models. Further experiments amount evidence that GPFs may generalize well to other machine learning tasks such as reinforcement learning in Atari, image classification, and autoregressive language models. We open source all code and data to encourage improvements on and more research in olfactory robotics.

Kordel K. France, Ovidiu Daescu

Department of Computer Science, University of Texas at Dallas, USA

Non-Stationary RLPartially Observable RLRobot NavigationContinual LearningAdaptive LearningNeural Network Pruning
AskPDF
May 24, 2026

SEED: Semi-supervised Continual MalwarE Detection for Tackling ConcEpt Drift on a BuDget

Machine learning based malware detectors become obsolete over time due to concept drift in benign and malware applications. Recent methods rely on fully labeled data and use hierarchical contrastive loss (HCL) with active learning to improve robustness against drift by exploiting semantic structure in malware representations. However, obtaining labeled data in the security domain is difficult. Under partially labeled settings, HCL suffers significant performance degradation in detecting unseen malware, especially on datasets such as BODMAS where strong semantic structure may not exist. In this paper, we propose SEED, a semantic-structure-agnostic method for malware detection under limited supervision. SEED combines a tailored binary cross-entropy objective with semi-supervised continual learning and active learning. For partially labeled seen tasks, unlabeled samples are projected into a representation space constructed from previously seen data using singular value decomposition, and paired with suitable labeled samples to encourage representation consistency. For unseen tasks with fully unlabeled data, uncertainty is quantified using cosine distance in representation space, and the most uncertain samples are selected for analyst labeling. We evaluate SEED on both Windows and Android malware datasets. Using only 20% labeled data on seen tasks, SEED achieves average AUT improvements of 40% on BODMAS and 14% on AndroZoo for unseen malware detection compared to HCL* (the semi-supervised adaptation of HCL), while remaining competitive on APIGraph. Finally, we introduce a delayed buffer update strategy to reduce label noise propagation during replay and improve learning stability.

Suresh Kumar Amalapuram, Bikraj Shresta, Siva Ram murthy Chebiyam +2

Indian Institute of Technology Ropar, India · Indian Institute of Technology Hyderabad, India

Concept DriftContinual LearningMalware ClassificationMalware AnalysisSemi-Supervised LearningMalware Detection
AskPDF
May 24, 2026

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems

Speech and audio systems operate in inherently non-stationary environments, yet continual learning (CL) research in this domain, especially in the foundation model era, remains fragmented that fail to account for the coupled, geometry-sensitive nature of acoustic representations. Modern speech foundation models operate over highly entangled, continuous representations that jointly encode linguistic, speaker, and paralinguistic factors within a shared latent space. CL is therefore fundamentally about preserving and evolving shared representation structure rather than retaining isolated task knowledge. In this work, we revisit CL for speech from a representation-centered perspective, and introduce a new taxonomy that organizes CL according to how underlying representation geometry evolves under non-stationary acoustic conditions. We further identify key mismatches between current CL assumptions and speech foundation model behavior, and finally outline a set of open challenges and future research directions.

Yang Xiao, Siyi Wang, Eun-Jung Holden +1

University of Melbourne, Melbourne, Australia.

Audio Representation LearningSpeech Foundation ModelsContinual LearningSpeech Processing
AskPDF
May 23, 2026

Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions

Legal NLP benchmarks evaluate models on randomly split data, implicitly assuming that legal language is stationary. We test this assumption by fine-tuning four transformer encoders -- XLM-RoBERTa (base and large) and their legal-domain variants -- on Ukrainian court decisions from three temporal epochs defined by geopolitical disruptions: pre-war (2008-2013), hybrid war (2014-2021), and full-scale invasion (2022-2026). Each model is trained on one epoch and evaluated on all three, producing a 3x3 cross-temporal generalization matrix. Four findings emerge. (1) Forward degradation is severe: models trained on pre-war data lose up to 27.2 percentage points of macro-F1 when applied to full-scale invasion era decisions. (2) The degradation is asymmetric: backward transfer (full-scale to pre-war) is substantially more robust than forward transfer, consistent with the hypothesis that legal language is additive. (3) Legal-domain pretraining (Legal-XLM-R) does not improve absolute performance but reduces forward degradation magnitude and asymmetry. (4) Chronological continual learning eliminates catastrophic forgetting for general XLM-R: pre-war knowledge is fully retained (+1.8 to +6.2 pp) while full-scale performance gains +16.5 to +19.0 pp; reverse-chronological training causes severe forgetting. Cross-jurisdictional pretraining on Swiss Judgment Prediction data improves absolute performance but does not reduce temporal degradation magnitude, confirming that temporal drift is an intrinsic property of legal language evolution. The dataset (428K decisions across three epochs) is publicly available as a LEXTREME contribution.

Volodymyr Ovcharov

Language Model PretrainingLegal NLPDistribution ShiftLegal Judgment PredictionContinual LearningTemporal Distribution Shift
AskPDF
May 20, 2026

Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning

Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge. Recent advances in large pre-trained models (LPMs) and model merging techniques, such as MAGMAX, have demonstrated effective CL performance by combining task-specific parameters. However, existing methods primarily focus on average performance across all tasks and do not adequately address how to construct models accommodating different deployment environments or varying user preferences. This paper proposes a model merging framework, termed Tunable MAGMAX, which enables preference-aware control of task-specific performance in CL. Our method introduces a preference vector that controls the number of elements selected from each task vector during model merging, allowing us to adjust the merged model performance according to their deployment needs. We further propose a method for automatically constructing appropriate preference vectors by leveraging small amounts of target environment data and datasets from model training tasks, thereby eliminating the need for manual specification. The experimental result on CL benchmark tasks demonstrates that Tunable MAGMAX effectively controls task-wise performance and successfully adapts merged models to various target environments. The proposed Tunable MAGMAX achieves superior or comparable performance to baseline methods, making it a practical solution for deploying CL models to various environments where the preferences of each task performance differ.

Kei Hiroshima, Kento Uchida, Shinichi Shirakawa

Yokohama National University, Yokohama Kanagawa 240-8501, Japan

Continual LearningLanguage Model MergingModel Merging
AskPDF
May 20, 2026

Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents

Language agents increasingly operate over streams of related tasks, yet existing memory systems struggle to convert accumulated experience into reusable knowledge. Retrieval-augmented and structured memory methods record per-session observations effectively, but often couple acquisition and consolidation into a single online process, leaving the agent without a global view across sessions to discover recurring patterns, abstract shared procedures, or prune redundant entries. Inspired by complementary learning systems theory, we propose Auto-Dreamer, a learned offline consolidator for language-agent memory. Auto-Dreamer decouples fast per-session memory acquisition from slow cross-session consolidation. Given a selected working region of a typed memory bank, the consolidator treats the region as read-only evidence, performs bounded tool-use to inspect entries and provenance-linked source trajectories, and synthesizes a fresh compact replacement set that abstracts across sessions and supersedes the original region. We train Auto-Dreamer via GRPO, using end-to-end agent performance as the reward signal to learn how to consolidate memories acquired through fast online experience. Trained on ScienceWorld trajectories alone, Auto-Dreamer outperforms fixed, RL-trained, and prompted memory baselines on ScienceWorld by 7 points while using an active memory bank 12×\times smaller than the strongest baseline, and continues to lead on held-out ALFWorld and WebArena without retraining -- using 6×\times less memory than the strongest baseline on ALFWorld.

Chongrui Ye, Yuxiang Liu, Yu Wang +5

University of Illinois Urbana-Champaign · University of California San Diego

Continual Learning for LLM AgentsContinual LearningLLM Agent MemoryPersistent Memory for Language ModelsMemory ConsolidationRL for LLM Agents
AskPDF
May 19, 2026

Continual Segmentation under Joint Nonstationarity

Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects practical structured prediction systems, yet remains largely unexplored in prior continual learning work, which typically studies these factors in isolation. We formalize continual segmentation under coupled class, domain, and label shifts and investigate learning in heterogeneous dense prediction environments with limited annotations and abundant unlabeled data. To address instability and overfitting arising from few-shot supervision under distribution drift, we introduce gradient-adaptive stabilization, a parameter-wise regularization mechanism implemented via gradient-scaled stochastic perturbations that promotes a principled stability-plasticity tradeoff. We further leverage unlabeled data through semi-supervised learning and introduce prototype anchored supervision that validates pseudo-labels via joint confidence and prototype consistency. Together, these mechanisms enable learning under joint nonstationarity in continual segmentation. Extensive empirical evaluation across class-incremental, domain-incremental, and few-shot regimes demonstrates consistent improvements over prior methods in heterogeneous structured prediction settings. Our results expose fundamental failure modes of existing continual segmentation approaches and provide insight into learning robust dense predictors in dynamically evolving environments.

Prashant Pandey, Himanshu Kumar, Devineni Sri Venkatraya Chowdary +1

Bharti School of Telecommunications Technology & Management, Indian Institute of Technology, Delhi, India · Yardi School of Artificial Intelligence, Indian Institute of Technology, Delhi, India · Department of Computer Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, India

Class-Incremental LearningContinual LearningFew-Shot Semantic SegmentationSemantic Segmentation
AskPDF
May 19, 2026

On-Device Continual Learning with Dual-Stage Buffer and Dynamic Loss for Point-of-Care Pneumonia Diagnosis

Deep learning models detect pneumonia from chest X-rays with high accuracy, but the performance declines under domain shifts caused by differences in devices, patients, or institutions. We present PneumoNet, a domain-incremental learning method for point-of-care pneumonia diagnosis in resource-limited settings. PneumoNet combines a lightweight CNN for on-device prediction, a dual-stage balanced buffer for class-balanced replay, and a dynamic class-weighted loss to correct training-batch imbalances. Evaluated on a domain-shifted PneumoniaMNIST dataset simulating five realistic domain change scenarios, PneumoNet achieves 86.6% accuracy with 1.4% forgetting while being smaller and faster than existing baselines. These results highlight PneumoNet's potential to enable adaptive, privacy-preserving diagnostic AI directly on point-of-care medical devices in real-world and pandemic-ready healthcare.

Danu Kim

Korea International School, Jeju Campus, Jeju-do 63644, Republic of Korea

Medical DiagnosisContinual LearningDomain-Incremental LearningMedical Image ClassificationOn-Device Inference
AskPDF
May 18, 2026

PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks

In the literature, many continual learning (CL) algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learning new tasks leads to the loss of performance on previously learned tasks). Although all CL approaches use some form of memory to retain information about past tasks, a grounded understanding of what information needs to be stored to minimize catastrophic forgetting remains elusive. Recently, it has been recognized that under the strong assumption of the existence of a common global minimizer over all tasks, catastrophic forgetting can be completely avoided. However, in practice, tasks rarely have a common global minimizer, and a certain amount of forgetting is inevitable. In this paper, we propose a foundational reframing of CL as balancing conflicting tasks in hindsight from a multi-task learning (MTL) perspective. The approach is based on finding Pareto-optimal solutions, i.e., the solutions which, by definition, minimally forget the previous tasks in the Pareto sense. We derive a Pareto-minimal-forgetting CL (PMF-CL) algorithm for linear and basis-function regression. Our algorithm naturally extends to loss functions with quadratic upper bounds around their minimizers, despite consuming only a static memory footprint of O(d2)O(d^2) for dd model parameters, independent of the number of sequentially occurring tasks TT. In the quadratic-loss setting, we obtain exact hindsight Pareto-optimal guarantees on forgetting. In the quadratic-upper-bound setting, forgetting is provably bounded, with the tightness of the forgetting bound being directly determined by the tightness of the quadratic bound on the loss function. Our numerical results validate our theoretical claims of convergence to the Pareto-optimal solution, and demonstrate that we consistently out-perform prior empirical methods while occupying lesser memory.

Srijith Nair, Atilla Eryilmaz, Jia Liu

Department of Electrical and Computer Engineering The Ohio State University Columbus, OH 43201

Continual LearningCatastrophic Forgetting
AskPDF