ICML 2026 Papers

Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors ($A$ and $B$), 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.

Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suffer from catastrophic forgetting, where learning new tasks degrades performance on earlier ones. We address this problem with **Shapley Neuron Valuation (SNV)**, a principled framework that quantifies Neuron importance in continual learning, grounded in cooperative game theory. SNV selectively freezes important Neurons while keeping others plastic, enabling **buffer-free** continual learning without expanding architecture. Experiments on ImageNet-1k show that SNV consistently outperforms existing buffer-free methods. In particular, SNV improves accuracy by **+2.88\%** in the class incremental learning and **+6.46\%** in the task incremental learning scenarios compared to the second baseline.

Custom diffusion models (CDMs) have demonstrated impressive success in visual personalization tasks by enabling the generation of user-specific concepts. However, existing CDMs typically assume that personalized concepts are static and rely on costly model merging or sequential updates that are prone to catastrophic forgetting as new concepts are introduced. To address these limitations, we propose a Submodular Concept Neuron Selection method (SCNS), to solve CDMs with continual personalized concepts, which formulates continual personalization as a constrained submodular optimization problem to select a minimal yet sufficient set of concept-specific neurons under diminishing returns. SCNS combines a Facility Location-based coverage objective to suppress semantic redundancy, a Fisher-weighted risk proxy to protect previously learned concepts, and a cost-aware greedy rule to balance stability and plasticity with extreme sparsity. Extensive experiments demonstrate that SCNS achieves state-of-the-art performance in image alignment and anti-forgetting, while enabling fusion-free continual personalization by modifying only 0.41% of the total parameters for each concept on average. Our implementation is available at SCNS.

Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shifts. Yet continual learning (CL) remains dominated by exo-only recognition tasks, obscuring behavior under these real-world coupled shifts. We introduce **C**ontinual **E**go, **E**xo, and **E**go-**E**xo **L**earning (**CE$^4$L**), a unified multi-view CL benchmark spanning four representative tasks: cross-view referenced skill assessment, temporal action segmentation, cross-view association, and action anticipation \& planning. CE$^4$L highlights challenges largely absent in prior CL benchmarks, including cross-view correspondence, view-dependent asynchrony, and heterogeneous semantic objectives. To this end, we propose **V**ideo **I**ncremental **S**ubspace-routed **T**ask **A**dapters (**VISTA**), a parameter-efficient baseline method that stores task-specific updates in lightweight adapters and performs training-free routing via residual distance to task-specific whitened subspaces estimated from second-order statistics. Extensive experiments demonstrate the significantly varied efficacy of representative CL methods across CE$^4$L settings, while VISTA is consistently competitive and achieves state-of-the-art overall performance.

Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting. Existing LoRA-based Mixture-of-Experts (MoE) methods expand capacity by adding isolated new experts while freezing old ones, but still suffer from redundancy, interference, routing ambiguity, and consequent forgetting. We investigate the issues stemming from coarse-grained expert granularity. Coarse-grained experts (e.g., high-rank LoRA) encode low-specialty information, leading to expert duplication/interference and routing degradation/confusion as experts accumulate. In this work, we propose MoRAM (Mixture of Rank-1 Associative Memory). Grounded in the view that weight matrices act as linear associative memories, MoRAM achieves CL as incremental expansion of reusable atomic rank-1 experts as memory. Each rank-1 adapter acts as a fine-grained MoE expert or an associative memory unit. By viewing rank-1 experts as key-value memory pairs, we eliminate explicit MoE-LoRA routers with self-activation, where each memory atom evaluates its relevance via its intrinsic key. The inference process thus becomes a content-addressable retrieval and recall over the incrementally accumulated memory of learning snapshots. Extensive experiments on CLIP and LLMs show that MoRAM significantly outperforms state-of-the-art methods, achieving a better plasticity–stability trade-off, stronger generalization, and reduced forgetting. Project page: https://artificer-ai-lab.github.io/MoRAM.

Continual learning of Vision-Language Model (VLM) aims to empower models with new expertise without compromising zero-shot capabilities. However, this pursuit faces a critical “dual-forgetting” challenge: catastrophic forgetting of newly acquired classes (Incremental Knowledge Forgetting, IKF) and erosion of foundational zero-shot capabilities (Pre-trained Knowledge Forgetting, PKF). Existing evaluations often ignore PKF or assess it via confounded protocols where positive transfer on semantically similar domains creates an illusion of retention, masking severe foundational degradation. To address this, we propose the Dual-Forgetting-Aware Class-Incremental Learning (DFA-CIL) framework and the Similarity-Calibrated Retention (SCR) metric. Unlike standard averaging, SCR uses the frozen pre-trained feature space to inversely weight performance by semantic similarity, mitigating confounding gains to stress-test foundational stability. Building on this, we propose DFA-MoE, a functionally heterogeneous Parameter-Efficient Fine-Tuning (PEFT) method. DFA-MoE decouples optimization objectives by assigning a momentum-enhanced contrastive expert for feature alignment, and separate plasticity experts combining classification with auxiliary contrastive learning to adapt to new tasks while retaining historical knowledge. Extensive experiments show that our framework reveals the hidden fragility of existing methods and achieves a state-of-the-art balance in preserving both incremental and pre-trained knowledge. Our code is available at https://github.com/RL-MIND/DFA-MoE.

Post-training endows pretrained LLMs with a variety of desirable skills, including instruction-following, reasoning, and others. However, these post-trained LLMs only encode knowledge up to a cut-off date, necessitating continual adaptation. Unfortunately, existing solutions cannot simultaneously learn new knowledge from an adaptation document corpora and mitigate the forgetting of earlier learned capabilities. To address this, we introduce Distillation via Split Contexts (DiSC), a simple context-distillation based approach for continual knowledge adaptation. DiSC derives student and teacher distributions by conditioning on distinct segments of the training example and minimizes the KL divergence between the shared tokens. This allows us to efficiently apply context-distillation without requiring explicit generation steps during training. We run experiments on four post-trained models and two adaptation domains. Compared to prior finetuning and distillation methods for continual adaptation, DiSC consistently reports the best trade-off between learning new knowledge and mitigating forgetting of previously learned skills like instruction-following, reasoning, and factual knowledge.

Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this phenomenon, we systematically compare the forgetting patterns of two widely adopted post-training methods: supervised fine-tuning (SFT) and reinforcement learning (RL). Our experiments reveal a consistent trend across LM families (Llama, Qwen) and tasks (instruction following, general knowledge, and arithmetic reasoning): RL leads to less forgetting than SFT while achieving comparable or higher target task performance. To investigate the cause for this difference, we consider a simplified setting in which the LM is modeled as a mixture of two distributions, one corresponding to prior knowledge and the other to the target task. We identify that the mode-seeking nature of RL, which stems from its use of on-policy data, enables keeping prior knowledge intact when learning the target task. We then verify this insight by demonstrating that the use on-policy data underlies the robustness of RL to forgetting in practical settings, as opposed to other algorithmic choices such as the KL regularization or advantage estimation. Lastly, as a practical implication, our results highlight the potential of mitigating forgetting using approximately on-policy data, which can be substantially more efficient to obtain than fully on-policy data.

We investigate why deep neural networks suffer from loss of plasticity in continual learning, and thus fail to learn new tasks without reinitializing parameters. We show that this failure is preceded by Hessian spectral collapse at new-task initialization, where meaningful curvature directions vanish and gradient descent becomes ineffective. Analyzing a linearized ReLU network, we derive explicit $\epsilon$-rank conditions for successful training and prove that the loss-weighted Gram matrix is spectrally equivalent to the Generalized Gauss-Newton approximation, thereby relating NTK dynamics to Hessian curvature. Targeting spectral collapse directly, we then discuss the Kronecker factored approximation of the Hessian, which motivates two regularization enhancements: maintaining high effective feature rank and applying L2 penalties. Experiments on continual supervised and reinforcement learning tasks confirm that combining these two regularizers effectively preserves plasticity.

Continual learning seeks to develop models capable of acquiring new tasks sequentially while retaining prior knowledge. A central challenge in this setting is managing inherent knowledge conflicts that arise as overlapping or contradictory information is introduced across tasks. While parameter-efficient fine-tuning (PEFT) techniques, particularly those based on Low-Rank Adaptation (LoRA), have shown promise by reducing interference through parameter isolation or modular architectures, they often treat conflict as something to avoid rather than address directly. In this work, we propose $\underline{S}$ubspace-$\underline{A}$ligned $\underline{B}$alanc$\underline{e}$d $\underline{R}$ecomposition (SABER), a novel method that reframes continual learning as a problem of structured conflict management. SABER introduces a unified subspace alignment framework to support shared task representations, decomposes task-specific knowledge into orthogonal components to preserve distinct information, and recomposes them using an energy-aware balancing mechanism that coordinates contributions without compromising stability. Extensive experiments across multiple continual learning benchmarks show that SABER achieves performance on par with or surpassing state-of-the-art methods, offering a principled approach that directly addresses the root cause of forgetting by managing representational conflict.

Federated Continual Learning (FCL) enables the continuous acquisition of knowledge from streaming tasks, but inherently struggles with the temporal dynamics of client data distributions. These dynamics naturally induce asynchronous concept drift, where distribution shifts occur independently across clients at unsynchronized times and with varying magnitudes. Such asynchrony generates conflicting updates that destabilize global convergence and exacerbate catastrophic forgetting. However, existing FCL research focuses on static or incremental settings, typically treating all incoming updates uniformly, which obscures concept drift under divergent distributions and fails to adapt to the evolution of learned concepts. To address these limitations, we propose RC-FCL, a retrospective calibration framework for FCL that can effectively distinguish asynchronous concept drift and adjust the learning strategy adaptively. Specifically, RC-FCL leverages a conditional generative model to synthesize class-conditional reference distributions of previously learned concepts for local drift detection. It calibrates local adaptation using a weighting mechanism driven by the local discriminator to prioritize informative samples, and executes a global aggregation strategy based on drift magnitude. Our experimental results demonstrate that RC-FCL achieves competitive performance against state-of-the-art methods.

AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two fundamental challenges: scaling model selection across thousands of experts and continually updating routing mechanisms as new models and tasks are introduced. In this paper, we formalise this setting as Continual Model Routing (CMR) and propose *CMRBench*, a new large-scale benchmark simulating realistic hub expansion and including over 2,000 candidate models. Finally, we introduce *CARvE*, a contrastive embedding approach for efficient continual model routing via domain-stratified coreset replay and checkpoint-based anchoring. Extensive empirical results and ablations show that CARvE significantly outperforms zero-shot retrieval, fine-tuning, and adapter-merging baselines in model, family, and domain-level accuracy.

Deploying robots in open-ended real-world environments demands continual learning capabilities to adapt to an ever-expanding range of tasks. This requires retaining previously acquired skills without forgetting while effectively leveraging prior knowledge to learn new ones. Inspired by neuroscience, we propose **N**euro-**e**volutionary **C**ontinual **R**einforcement **L**earning (**Nevo-CRL**). Nevo-CRL maintains a fixed-capacity monolithic policy network, solving tasks by optimizing inter-layer connectivity and neuron parameters. For each new task, Nevo-CRL constructs a mask population to selectively activate the outputs of each hidden layer, thereby forming a task-specific policy population. Upon completing each task, the best-performing mask is stored, and its activated neurons are frozen to prevent catastrophic forgetting. To facilitate knowledge transfer, Nevo-CRL reuses neurons from acquired skills based on semantic similarity between tasks, while dynamically allocating additional neurons for task-specific adaptation. In the learning process, Nevo-CRL iteratively adjusts masks via importance-guided crossover to optimize the policy network connectivity. To improve neuron utilization, we prune low-activity connections to recycle neurons. Experiments demonstrate that Nevo-CRL achieves state-of-the-art performance among continual RL methods. The code is available at [https://github.com/yeshenpy/Nevo-CRL](https://github.com/yeshenpy/Nevo-CRL).

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious, domain-specific cues ("shortcut learning"), which limits generalization to unseen domains after deployment. In this paper, we address this limitation through *continual learning of domain-invariant representation*. We introduce a broad class of CL methods that sequentially learn representations capturing invariant structures across domains. Our methods are motivated by the observation that such invariant structures often preserve the underlying causal mechanisms, which can reduce the risk of overfitting to domain-specific cues and thus offer better out-of-domain generalization. Our proposed CL methods combine replay-based training with a tailored sequential invariance alignment to learn---and preserve---invariant structures over time. We evaluate our methods under a deployment-oriented protocol that measures performance on unseen target domains. Across six benchmark and real-world datasets spanning vision, medicine, manufacturing, and ecology, our methods consistently outperform existing CL baselines in terms of generalization to unseen target domains. As an ablation, we further show that naïve extensions of sequential training with existing domain-invariant representation learning (DIRL) methods provide only limited benefits. To the best of our knowledge, this is the first work to develop domain-invariant representation methods for CL.

Pretraining optimizers are tuned to produce the strongest possible base model, on the assumption that a stronger starting point yields a stronger model after subsequent changes like post-training and quantization. This overlooks the geometry of the base model which controls how much of the base model's capabilities survive subsequent parameter updates. We study three pretraining optimization approaches that bias optimization toward flatter minima: Sharpness-Aware Minimization (SAM), large learning rates, and shortened learning rate annealing periods. Across model sizes ranging from 20M to 150M parameters, we find that these interventions consistently improve downstream performance after post-training on five common datasets with up to 80\% less forgetting. These principles hold at scale: a short SAM mid-training phase applied to an existing OLMo-2-1B checkpoint reduces forgetting by 31\% after MetaMath post-training and by 40\% after 4-bit quantization.

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task settings, while real-world prompts often contain sequences of heterogeneous tasks, leaving a gap in understanding whether Large Language Models implicitly perform continual learning during inference. To bridge this gap, we propose the first theoretical framework for in-context continual learning, modeling how a pretrained Transformer processes multiple sequential tasks within a single prompt through shared attention mechanisms. Focusing on linear and masked linear self-attention, we derive error expressions for model predictions under sequential task prompts and analyze their generalization and forgetting behavior. Our results reveal that standard attention mechanisms inevitably induce inter-task interference by uniformly or causally aggregating historical contexts, leading to systematic bias. We further provide a bias–variance–interference decomposition of prediction error, characterizing when historical in-context information yields positive transfer or provable negative transfer. This analysis exposes fundamental limits of attention-based continual inference and offers theoretical explanations for order sensitivity and performance degradation in long prompts.

Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open problem: fine-tuning and parameter-efficient variants risk catastrophic forgetting, while context-based approaches have limited expressiveness and are constrained by the model's effective context. We explore *skill neologisms*--soft tokens integrated in the model's vocabulary and optimized to improve capabilities over a specific skill--as a way to selectively acquire new skills without weight updates. We first observe that pre-trained LLMs already exhibit tokens associated with procedural knowledge. We then show on a controlled synthetic task that skill neologisms can be learned to improve model capabilities on specific skills while being composable with out-of-distribution skills, and that independently trained skill neologisms can be composed zero-shot. Finally, we validate zero-shot composition of independently learned skill neologisms on the more realistic natural language setting of the Skill-Mix benchmark. These results suggest that skill neologisms may provide a scalable path towards skill-based continual learning.

Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision—a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce stability of individual node (or node-pair) embeddings. Due to optimizing nodes in isolation, these methods fail to maintain global relational structure, causing inter-node correspondences to progressively distort under continual learning. To this end, we propose a novel Structure-Aware Optimal Transport (SAOT) framework that explicitly captures and preserves relational structure within graph representations across sequential tasks. Specifically, SAOT leverages optimal transport theory to capture global inter-node correspondences, thereby facilitating and enhancing graph representation learning. Simultaneously, SAOT incorporates a cross-task knowledge distillation mechanism to preserve the previous structural knowledge. Extensive experiments on four CGL benchmark datasets demonstrate that SAOT outperforms existing self-supervised baselines. In particular, SAOT achieves significant performance gains, improving average accuracy by up to 5% on CoraFull-CL and over 15% on Products-CL compared with state-of-the-art methods in the Class-IL setting.

Research on continual learning for LLMs seeks to acquire new skills without catastrophic forgetting of established prior knowledge. However, domain-specific fine-tuning still triggers severe, long-tailed forgetting issues even under narrow updates, particularly when the pre-training data is inaccessible. To tackle this challenge, we propose **ALER**, a data-free continual learning framework that adversarially searches for a small set of latent prompt embeddings to maximize logit divergence from a frozen reference model, proactively exposing high-risk forgetting modes at each step. It then performs online distillation from the frozen reference using the discovered embeddings to retain prior behaviors while preserving target-domain adaptation. We provide theoretical guarantees on the efficiency of our targeted repair, and extensive experiments demonstrate consistent improvements in the retention–adaptation frontier over representative baselines across $2$ domain-specific fine-tuning datasets and $6$ general-purpose benchmarks, suggesting a more proactive approach for LLM continual learning.