SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.11549 · CVPR · 2024

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

Lu Zhang, Dong Wang, Huchuan Lu, Jiazuo Yu, Yunzhi Zhuge, Ping Hu, You He

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.11549.json · badge: /api/ran/2403.11549.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
jiazuoyu/moe-adapters4cl canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
JiazuoYu/MoE-Adapters4CL community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Adapter Ran
ran on a synthesized input · constructed an object; no result was computed
JiazuoYu/MoE-Adapters4CL/cil/clip/adapter.py
pointer only (licence: NONE) · get_code("97237f25b2120465")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JiazuoYu/MoE-Adapters4CL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

project_logits Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiazuoyu/moe-adapters4cl/cil/datasets_ref/imagenet.py
pointer only (licence: NONE) · get_code("9fbea808db47dc66")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiazuoyu/moe-adapters4cl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_model Not yet run
unverified (harvested, no recorded run)
jiazuoyu/moe-adapters4cl/cil/clip/model.py
pointer only (licence: NONE) · get_code("4db506dabde16a1f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiazuoyu/moe-adapters4cl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_classnames Not yet run
unverified (harvested, no recorded run)
jiazuoyu/moe-adapters4cl/cil/datasets_ref/imagenet_classnames.py
pointer only (licence: NONE); the stored copy get_code serves, from BeierZhu/VRF, is pointer only (licence: NONE) · get_code("3903d266387afea6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiazuoyu/moe-adapters4cl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 3 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
project_logits 7 other papers
3 dated earlier, 1 the same month, 3 later
2303.16203 (2023-03)
Your Diffusion Model is Secretly a Zero-Shot Classifier
2311.01723 (2023-11)
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
2312.02546 (2023-12)
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
and 4 more not named here
get_classnames 4 other papers
1 dated earlier, 1 the same month, 2 later
2312.02546 (2023-12)
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
2403.10245 (2024-03)
CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
2406.03345 (2024-06)
Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
and 1 more not named here
build_model 2 other papers
1 later, 1 undated
Kang_Dynamic_Multi-Layer_Null_Space_Projection_for_Vision-Language_Continual_Learning_ICCV_2025_paper (2025 (year only))
Dynamic Multi-Layer Null Space Projection for Vision-Language Continual Learning
openreview_ZPJbTXMYft
Mixing Expertise with Confidence: A Mixture of Experts Framework for Robust Multi-Modal Continual Learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial due to (i) parameter shifts throughout lifelong learning and (ii) significant computational burdens associated with full-model tuning. In this work, we present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters in response to new tasks. To preserve the zero-shot recognition capability of vision-language models, we further introduce a Distribution Discriminative Auto-Selector (DDAS) that automatically routes in-distribution and out-of-distribution inputs to the MoE Adapter and the original CLIP, respectively. Through extensive experiments across various settings, our proposed method consistently outperforms previous state-of-the-art approaches while concurrently reducing parameter training burdens by 60%. Our code locates at https://github.com/JiazuoYu/MoE-Adapters4CL * Corresponding author data with historical datasets. In contrast, Continual Learning (CL), offering an efficient incremental training strategy, emerges as a solution by focusing on new data at each training stage. However, CL faces the significant hurdle of "catastrophic forgetting" where a model loses previously acquired knowledge upon learning new tasks [24,52]. To remedy this issue, one of the popular solutions in current CL methods [1,16,23,43] is to develop dynamic expansion frameworks by incrementally adding task-specific components to a shared base model (see Figure 1 (a)). Although these methods show promise in memorization and scalability, they cannot distinguish unseen data and thus overlook zero-shot transfer capability. Recent advancements like ZSCL [79] have brought the zero-shot transfer ability into continual learning by leveraging a pretrained Vision Language Model (VLM). As illustrated in Figure 1 (b), this method relies on knowledge distillation to integrate zero-shot generalization ability from the frozen CLIP and uses parameter regularization to prevent knowledge degradation in continual learning. However, these designs often entail large computational burdens and exhibit limitations in long-term memorization. It's then natural to ask whether we can combine the merits of the pretrained foundation model and dynamic expansion strategy to form an effective system with robust memorization and zero-shot transfer abilities. Recently, Parameter-Efficient Fine-Tune (PEFT) methods [22,28,30,66,74,77] have demonstrated that largescale models can quickly adapt to downstream tasks via only fine-tuning less-parameterized adapters. This inspires us to build a dynamic expansion framework on VLM with task-specific adapters to relieve the parameter burdens in long-term CL. Nevertheless, the intuitive approach of stacking adapters during incremental learning introduces a dependency on task identity. This poses challenges in practical scenarios such as class incremental learning where task identity may be unavailable. Furthermore, the use of independent adapters neglects the potential for inter-task knowl-This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.11549")
get_code_for_paper("2403.11549")
have("2403.11549")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.11549.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.11549.svg)](https://syntology.ai/paper/2403.11549)

Connect an agent — have() is free.