SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.02539 · ICML · 2025

Parrot: Multilingual Visual Instruction Tuning

Han-Jia Ye, De-Chuan Zhan, Weihua Luo, Zhao Xu, Yang Li, Da-Wei Zhou, Hai-Long Sun, Shiyin Lu, Chao Yi, Qing-Guo Chen, Kaifu Zhang, A Balıkçılar, and 7 more

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 4 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/2406.02539.json · badge: /api/ran/2406.02539.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
AIDC-AI/Parrot canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
aidc-ai/parrot alias (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
build_vision_projector Ran
ran; our contract draft was wrong, not the code
AIDC-AI/Parrot/parrot/model/multimodal_projector/builder.py
code served (permissive licence) · get_code("ef4db0da176c674c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Linear. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class Config:
    def __init__(self, mm_projector_type, mm_hidden_size, hidden_size):
        self.mm_projector_type = mm_projector_type
        self.mm_hidden_size = mm_hidden_size
        self.hidden_size = hidden_size

# Test with 'linear' projector type
config_linear = Config(mm_projector_type='linear', mm_hidden_size=4, hidden_size=3)

ARGS = {
    'config': config_linear,
    'delay_load': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
split_to_even_chunks Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AIDC-AI/Parrot/parrot/train/parrot_trainer.py
code served (permissive licence) · get_code("10893c4608c08075")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Analyzing the function:
# - indices: a list/sequence of indices that will be iterated over
# - lengths: a dict-like or list-like object that maps indices to their lengths (accessed via lengths[index])
# - num_chunks: an integer specifying how many chunks to split into

# Create sample data
indices = [0, 1, 2, 3, 4, 5]
lengths = {0: 10, 1: 15, 2: 8, 3: 12, 4: 9, 5: 11}
num_chunks = 3

ARGS = {
    "indices": indices,
    "lengths": lengths,
    "num_chunks": num_chunks,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
unpad_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AIDC-AI/Parrot/parrot/model/parrot_arch.py
code served (permissive licence) · get_code("7606525af238fb64")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 3, dtype family float, shape (3, 8, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a padded image tensor in CxHxW format
# C=3 (RGB), H=8 (current height), W=6 (current width)
tensor = torch.randn(3, 8, 6)

# Original size as (width, height)
# Using different dimensions to be distinct: width=4, height=5
original_size = (4, 5)

ARGS = {
    "tensor": tensor,
    "original_size": original_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 8, 6) — shape (3, 8, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ParrotMetaForCausalLM Not yet run
unverified (harvested, no recorded run)
aidc-ai/parrot/parrot/model/parrot_arch.py
code served (permissive licence) · get_code("fd2cc4319a956bc2")
How it ran

no invocation recorded.

build_vision_tower Not yet run
unverified (harvested, no recorded run)
AIDC-AI/Parrot/parrot/model/multimodal_encoder/builder.py
code served (permissive licence) · get_code("aeaec2cd790d9027")
How it ran

no invocation recorded.

get_mm_adapter_state_maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
AIDC-AI/Parrot/parrot/train/parrot_trainer.py
code served (permissive licence) · get_code("bb35e3ac741bb2c9")
How it ran

no invocation recorded.

maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
AIDC-AI/Parrot/parrot/train/parrot_trainer.py
code served (permissive licence) · get_code("735025744c1ab0cf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 5 the same month, 5 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
unpad_image
brick of this paper's assembly: helper
69 other papers
9 dated earlier, 7 the same month, 53 later · 5 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2309.09958 (2023-09)
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
2310.03744 (2023-10)
Improved Baselines with Visual Instruction Tuning
and 66 more not named here
get_mm_adapter_state_maybe_zero_3 43 other papers
15 dated earlier, 4 the same month, 24 later
2304.05884 (2023-04)
Unicom: Universal and Compact Representation Learning for Image Retrieval
2304.08485 (2023-04)
Visual Instruction Tuning
2310.03744 (2023-10)
Improved Baselines with Visual Instruction Tuning
and 40 more not named here
maybe_zero_3 42 other papers
16 dated earlier, 4 the same month, 22 later
2304.05884 (2023-04)
Unicom: Universal and Compact Representation Learning for Image Retrieval
2304.08485 (2023-04)
Visual Instruction Tuning
2310.03744 (2023-10)
Improved Baselines with Visual Instruction Tuning
and 39 more not named here
split_to_even_chunks 40 other papers
14 dated earlier, 4 the same month, 22 later
2304.05884 (2023-04)
Unicom: Universal and Compact Representation Learning for Image Retrieval
2304.08485 (2023-04)
Visual Instruction Tuning
2310.03744 (2023-10)
Improved Baselines with Visual Instruction Tuning
and 37 more not named here
build_vision_projector 17 other papers
6 dated earlier, 3 the same month, 8 later · 13 only as an assembly brick
2301.12597 (2023-01)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
2304.08485 (2023-04)
Visual Instruction Tuning
2402.18695 (2024-02)
Grounding Language Models for Visual Entity Recognition
and 14 more not named here

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

The rapid development of Multimodal Large Language Models (MLLMs), such as GPT-4o, marks a significant step toward artificial general intelligence. Existing methods typically align vision encoders with LLMs via supervised finetuning (SFT), but this often deteriorates their ability to handle multiple languages as training progresses. We empirically observe that imbalanced SFT datasets, largely English-centric, degrade performance on non-English languages due to the failure in multilingual token alignment. To address this, we propose PARROT, a novel approach that leverages textual guidance for visual token alignment at the language level. PARROT conditions visual tokens on diverse language inputs and uses Mixture-of-Experts (MoE) to align multilingual tokens. By computing cross-attention between initial visual features and textual embeddings, we select the most relevant experts, converting visual tokens into language-specific representations. Additionally, we introduce the Massive Multilingual Multimodal Benchmark (MMMB), a new benchmark comprising 6 languages, 15 categories, and 12,000 questions, to assess multilingual capabilities. PARROT achieves stateof-the-art performance on both the multilingual benchmarks and a wide range of multimodal tasks. Code and dataset are available at: https: //github.com/AIDC-AI/Parrot.

For agents

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

get_harvested_code_for_paper("2406.02539")
get_code_for_paper("2406.02539")
have("2406.02539")

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

curl https://syntology.ai/api/ran/2406.02539.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.02539.svg)](https://syntology.ai/paper/2406.02539)

Connect an agent — have() is free.