Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models

• URL: http://arxiv.org/abs/2603.21170v1
• Date: Sun, 22 Mar 2026 11:15:34 GMT
• Title: Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models
• Abstract summary: Pruned Adaptation Modules (PAM) is a simple yet effective method that freezes the vast majority of the pre-trained ResNet.<n>PAM consistently mitigates catastrophic forgetting and outperforms state-of-the-art FM-based CIL approaches.
• Score: 9.273551382858525
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The continual learning literature has rapidly shifted from traditional class incremental learning (CIL) techniques to foundation model (FM)-based CIL methods without a clear understanding of how these newer approaches compare to strong, lightweight convolutional baselines. This abrupt transition has created a substantial methodological gap, making it difficult to assess whether recent FM-based CIL progress reflects genuine advances or merely the absence of rigorous baselines. To address this gap, we introduce Pruned Adaptation Modules (PAM), a simple yet effective method that freezes the vast majority of the pre-trained ResNet while enabling scalable continual adaptation through sparse task-specific layers. PAM yields up to a ~5x reduction in trainable parameters and a ~6x reduction in total parameters, significantly reducing the cost of continual updates. Across diverse benchmarks, PAM consistently mitigates catastrophic forgetting and outperforms state-of-the-art FM-based CIL approaches. Our findings position PAM as a strong and transparent baseline that helps bridge the gap between traditional and FM-based CIL, guiding future research for a more accurate assessment of true progress in continual adaptation. The code can be found at: https://github.com/ElifCerenGokYildirim/PAM.

Related papers

• RL Forgets! Towards Continual Policy Optimization [57.4336338996653]
  Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.<n>Recent work has increasingly favored reinforcement learning over supervised fine-tuning, driven by the belief that reinforcement learning is inherently less prone to forgetting.<n>We propose Continual Policy Optimization (CPO), a replay-free framework grounded in a prior-task behavioral KL objective.
  arXiv  Detail & Related papers  (2026-07-05T15:46:11Z)
• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators [0.4369550829556577]
  New experimental conditions or simulation regimes may differ significantly, requiring extrapolation and model updates without re-access to prior data.<n>This creates a need for continual learning (CL) frameworks that can adapt to distribution shifts while preventing catastrophic forgetting.<n>We introduce a new architecture-based approach (SLE-FNO) combining a Single-Layer Extension (SLE) with the Fourier Neural Operator (FNO) to support efficient CL.
  arXiv  Detail & Related papers  (2026-03-20T18:30:38Z)
• Forward-Only Continual Learning [8.873948519614244]
  Catastrophic forgetting remains a central challenge in continual learning.<n>We propose FoRo, a forward-only, gradient-free continual learning method.<n>Experiments show that FoRo significantly reduces average forgetting and improves accuracy.
  arXiv  Detail & Related papers  (2025-09-01T15:10:38Z)
• MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models [28.79185891706149]
  Diffusion language models suffer from a key discrepancy between training and inference.<n>We propose a novel Masked Diffusion Policy Optimization (MDPO) to exploit the Markov property diffusion.<n>Our findings establish great potential for investigating the discrepancy between pre-training and inference of MDLMs.
  arXiv  Detail & Related papers  (2025-08-18T17:58:13Z)
• WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training [64.0932926819307]
  We present Warmup-Stable and Merge (WSM), a framework that establishes a formal connection between learning rate decay and model merging.<n>WSM provides a unified theoretical foundation for emulating various decay strategies.<n>Our framework consistently outperforms the widely-adopted Warmup-Stable-Decay (WSD) approach across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-07-23T16:02:06Z)
• Fast and Stable Diffusion Planning through Variational Adaptive Weighting [3.745003761050674]
  Diffusion models have recently shown promise in offline RL.<n>These methods often suffer from high training costs and slow convergence.<n>We introduce a closed-form approximation method for its online estimation under the flow-based generative modeling framework.<n> Experimental results on Maze2D and Kitchen tasks show that our method achieves competitive performance with up to 10 times fewer training steps.
  arXiv  Detail & Related papers  (2025-06-20T02:12:04Z)
• Beyond Freezing: Sparse Tuning Enhances Plasticity in Continual Learning with Pre-Trained Models [10.904981532789824]
  Continual Learning with Pre-trained Models holds great promise for efficient adaptation across sequential tasks.<n>Existing approaches freeze PTMs and rely on auxiliary modules like prompts or adapters.<n>We propose Mutual Information-guided Sparse Tuning (MIST), a plug-and-play method that selectively updates a small subset of PTM parameters.
  arXiv  Detail & Related papers  (2025-05-26T13:09:25Z)
• SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training [68.7896349660824]
  We present an in-depth analysis of the progressive overfitting problem from the lens of Seq FT. Considering that the overly fast representation learning and the biased classification layer constitute this particular problem, we introduce the advanced Slow Learner with Alignment (S++) framework. Our approach involves a Slow Learner to selectively reduce the learning rate of backbone parameters, and a Alignment to align the disjoint classification layers in a post-hoc fashion.
  arXiv  Detail & Related papers  (2024-08-15T17:50:07Z)
• Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models [70.15122130694256]
  We show how P-RFCL techniques can be matched by a simple and lightweight PEFT baseline.<n>We show how most often, P-RFCL techniques can be matched by a simple and lightweight PEFT baseline.
  arXiv  Detail & Related papers  (2024-06-13T17:57:10Z)
• Meta-Learning with Adaptive Hyperparameters [55.182841228303225]
  We focus on a complementary factor in MAML framework, inner-loop optimization (or fast adaptation) We propose a new weight update rule that greatly enhances the fast adaptation process.
  arXiv  Detail & Related papers  (2020-10-31T08:05:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.