SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.10667 · ICLR · 2024

Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond

Ruirui Li, Zhengyang Wang, Jingrui He, Xianfeng Tang, Tianxin Wei, Jianhui Sun, Hanqing Lu, Suhang Wang, Jin Bowen, Hansi Zeng, Qingyu Yin

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 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/2403.10667.json · badge: /api/ran/2403.10667.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
weitianxin/UniMP canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
weitianxin/UniMP/UniMP/xformers_model/llama.py
pointer only (licence: NONE) · get_code("f725bc2d76076485")
How it ran

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

compute_classification_accuracy Ran
ran, honoured the contract we drafted
weitianxin/UniMP/UniMP/pipeline/eval/classification.py
pointer only (licence: NONE) · get_code("ec8c233fb6abbe44")
How it ran

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

compute_shifted_logits_and_labels Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
weitianxin/UniMP/UniMP/pipeline/eval/classification.py
pointer only (licence: NONE) · get_code("4fbef42363d6fcd6")
How it ran

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

get_formatted_prompt Ran
ran; our contract draft was wrong, not the code
weitianxin/UniMP/UniMP/pipeline/eval/benchmark_otter.py
pointer only (licence: NONE) · get_code("e1ef1e3160bff234")
How it ran

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

get_response Ran
ran; our contract draft was wrong, not the code
weitianxin/UniMP/UniMP/pipeline/eval/benchmark_otter.py
pointer only (licence: NONE) · get_code("8b8566f333cb4974")
How it ran

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

postprocess_captioning_generation Ran
ran; our contract draft was wrong, not the code
weitianxin/UniMP/UniMP/pipeline/eval/coco_metric.py
pointer only (licence: NONE) · get_code("fc91265a186bcbd4")
How it ran

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

postprocess_classification_generation Ran
ran; our contract draft was wrong, not the code
weitianxin/UniMP/UniMP/pipeline/eval/classification.py
pointer only (licence: NONE) · get_code("a666b1cfb752e8e7")
How it ran

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

rotate_half Ran
ran; our contract draft was wrong, not the code
weitianxin/UniMP/UniMP/xformers_model/llama.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
How it ran

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

get_image Not yet run
unverified (harvested, no recorded run)
weitianxin/UniMP/UniMP/pipeline/eval/benchmark_otter.py
pointer only (licence: NONE) · get_code("3217afe4fa565c58")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weitianxin/UniMP 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 3 later) and 3 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
rotate_half 360 other papers
94 dated earlier, 8 the same month, 249 later, 6 same year, order not determinable, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
apply_rotary_pos_emb 83 other papers
31 dated earlier, 2 the same month, 48 later, 2 same year, order not determinable · 6 only as an assembly brick
2306.15595 (2023-06)
Extending Context Window of Large Language Models via Positional Interpolation
2307.05695 (2023-07)
ReLoRA: High-Rank Training Through Low-Rank Updates
2307.06945 (2023-07)
In-context Autoencoder for Context Compression in a Large Language Model
and 80 more not named here
postprocess_captioning_generation 3 other papers
1 dated earlier, 2 later
2310.00647 (2023-10)
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
2406.08418 (2024-06)
OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
2408.05926 (2024-08)
BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation
compute_classification_accuracy 1 other paper
1 dated earlier
2310.00647 (2023-10)
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
compute_shifted_logits_and_labels 1 other paper
1 dated earlier
2310.00647 (2023-10)
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
postprocess_classification_generation 1 other paper
1 dated earlier
2310.00647 (2023-10)
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context 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

Developing a unified model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration. Our daily choices, especially in domains like fashion and retail, are substantially shaped by multi-modal data, such as pictures and textual descriptions. The vision and language modalities not only offer intuitive guidance but also cater to personalized user preferences. However, the predominant personalization approaches mainly focus on the ID or text-based recommendation problem, failing to comprehend the information spanning various tasks or modalities. In this paper, our goal is to establish a Unified paradigm for Multi-modal Personalization systems (UniMP), which effectively leverages multi-modal data while eliminating the complexities associated with task-and modality-specific customization. We argue that the advancements in foundational generative modeling have provided the flexibility and effectiveness necessary to achieve the objective. In light of this, we develop a generic and extensible personalization generative framework, that can handle a wide range of personalized needs including item recommendation, product search, preference prediction, explanation generation, and further userguided image generation. Our methodology enhances the capabilities of foundational language models for personalized tasks by seamlessly ingesting interleaved vision-language user history information, ensuring a more precise and customized experience for users. To train and evaluate the proposed multi-modal personalized tasks, we also introduce a novel and comprehensive benchmark covering a variety of user requirements. Our experiments on the real-world benchmark showcase the model's potential, outperforming competitive methods specialized for each task. § Work was done while Tianxin, Bowen, Hansi, Jianhui were interning at Amazon.

For agents

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

get_harvested_code_for_paper("2403.10667")
get_code_for_paper("2403.10667")
have("2403.10667")

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

curl https://syntology.ai/api/ran/2403.10667.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.10667.svg)](https://syntology.ai/paper/2403.10667)

Connect an agent — have() is free.