SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.01639 · 2026

ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval

Jinqiao Wang, Tat-Seng Chua, Leigang Qu, Tianyu Yang, Haiyun Guo, Tianyue Wang, Xiangzhao Hao, Chenwei He, Jiarui Guo

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2602.01639.json · badge: /api/ran/2602.01639.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
RemRico/Recall canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
dist_gather Ran
ran, honoured the contract we drafted
RemRico/Recall/src/dist_utils.py
pointer only (licence: NONE) · get_code("230ef02dd4dd96d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RemRico/Recall 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.

dist_gather_nograd Ran
ran, honoured the contract we drafted
RemRico/Recall/src/dist_utils.py
pointer only (licence: NONE) · get_code("89f1c28d66196e80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RemRico/Recall 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.

infer_base_model_from_checkpoint Ran
ran; our contract draft was wrong, not the code
RemRico/Recall/eval_fashioniq.py
pointer only (licence: NONE) · get_code("7b61e2e3c86cceb8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RemRico/Recall 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.

setup_device Ran
ran; our contract draft was wrong, not the code
RemRico/Recall/eval_fashioniq.py
pointer only (licence: NONE) · get_code("0a74668bbf6c7dbc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RemRico/Recall 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.

varsize_gather_nograd Ran
ran, honoured the contract we drafted
RemRico/Recall/src/dist_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from facebookresearch/contriever, is pointer only (licence: NOASSERTION) · get_code("b1ad8cd3a7168b7f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RemRico/Recall 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
varsize_gather_nograd 10 other papers
9 dated earlier, 1 later
2402.03216 (2024-02)
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
2402.07867 (2024-02)
PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
2403.06840 (2024-03)
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
and 7 more not named here
dist_gather 1 other paper
1 dated earlier
2510.00523 (2025-10)
VIRTUE: Visual-Interactive Text-Image Universal Embedder
dist_gather_nograd 1 other paper
1 dated earlier
2510.00523 (2025-10)
VIRTUE: Visual-Interactive Text-Image Universal Embedder

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

Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models (VLMs) struggle with crossmodality compositional reasoning required for this task. While adapting generative Multimodal Large Language Models (MLLMs) for retrieval offers a promising direction, we identify that this strategy overlooks a fundamental issue: compressing a generative MLLM into a singleembedding discriminative retriever triggers a paradigm conflict, which leads to Capability Degradation-the deterioration of native fine-grained reasoning after retrieval adaptation. To address this challenge, we propose Re-CALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline: First, we diagnose cognitive blind spots of the retriever via self-guided informative instance mining. Next, we generate corrective instructions and triplets by prompting the foundation MLLM and conduct quality control with VQA-based consistency filtering. Finally, we refine the retriever through continual training on these triplets with a grouped contrastive scheme, thereby internalizing fine-grained visual-semantic distinctions and realigning the discriminative embedding space of retriever with intrinsic compositional reasoning within the MLLM. Extensive experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance. Code is available at https://github.com/RemRico/Recall.

For agents

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

get_harvested_code_for_paper("2602.01639")
get_code_for_paper("2602.01639")
have("2602.01639")

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

curl https://syntology.ai/api/ran/2602.01639.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.01639.svg)](https://syntology.ai/paper/2602.01639)

Connect an agent — have() is free.