SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.21646 · 2026

Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion

Bo Yang, Ming Liu, Bing Qin, Zekun Wang, Zheng Chu, Yang Xiang, Kaiyuan Liu, Yichong Huang, Youcheng Pan, Yexing Du

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; 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/2602.21646.json · badge: /api/ran/2602.21646.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
yxduir/LLM-SRT canonical (classifier label)
classifier basis: census
3 ran · 4 no recorded run
FunctionStatusWhere it lives
load_label Ran
ran; our contract draft was wrong, not the code
yxduir/LLM-SRT/SLAM-LLM/src/slam_llm/datasets/avhubert_dataset.py
pointer only (licence: NONE) · get_code("113a523619225ba0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yxduir/LLM-SRT 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.

load_label_offset Ran
ran; our contract draft was wrong, not the code
yxduir/LLM-SRT/SLAM-LLM/src/slam_llm/datasets/avhubert_dataset.py
pointer only (licence: NONE) · get_code("3e9450b6ac2fcddd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yxduir/LLM-SRT 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.

read_dialogs_from_file Ran
ran; our contract draft was wrong, not the code
yxduir/LLM-SRT/SLAM-LLM/src/slam_llm/inference/chat_utils.py
pointer only (licence: NONE) · get_code("8922fb4b5b7006f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yxduir/LLM-SRT 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.

format_tokens Not yet run
unverified (harvested, no recorded run)
yxduir/LLM-SRT/SLAM-LLM/src/slam_llm/inference/chat_utils.py
pointer only (licence: NONE) · get_code("d6e79a515a6d6ba6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yxduir/LLM-SRT 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_audio_dataset Not yet run
unverified (harvested, no recorded run)
yxduir/LLM-SRT/SLAM-LLM/src/slam_llm/datasets/avsr_dataset.py
pointer only (licence: NONE) · get_code("48e3739a0901fbda")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yxduir/LLM-SRT 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_text_dataset Not yet run
unverified (harvested, no recorded run)
yxduir/LLM-SRT/SLAM-LLM/src/slam_llm/datasets/text_dataset.py
pointer only (licence: NONE) · get_code("9d08959e871bb637")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yxduir/LLM-SRT 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.

load_audio_visual Not yet run
unverified (harvested, no recorded run)
yxduir/LLM-SRT/SLAM-LLM/src/slam_llm/datasets/avhubert_dataset.py
pointer only (licence: NONE) · get_code("f0641584d0fe0fb5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yxduir/LLM-SRT 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 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, 0 the same month, 0 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
load_label 4 other papers
4 dated earlier
2312.02512 (2023-12)
AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
2401.03468 (2024-01)
Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
2402.15151 (2024-02)
Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing
and 1 more not named here
load_label_offset 4 other papers
4 dated earlier
2312.02512 (2023-12)
AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
2401.03468 (2024-01)
Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
2402.15151 (2024-02)
Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing
and 1 more not named here
load_audio_visual 3 other papers
3 dated earlier
2312.02512 (2023-12)
AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
2402.15151 (2024-02)
Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing
2407.03563 (2024-07)
Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition
read_dialogs_from_file 3 other papers
3 dated earlier
2404.01099 (2024-04)
What is in Your Safe Data? Identifying Benign Data that Breaks Safety
2410.10343 (2024-10)
Locking Down the Finetuned LLMs Safety
2025.findings-acl.337 (2025 (year only))
The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?
format_tokens 2 other papers
2 dated earlier
2404.01099 (2024-04)
What is in Your Safe Data? Identifying Benign Data that Breaks Safety
2410.10343 (2024-10)
Locking Down the Finetuned LLMs Safety

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

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is constrained by the scarcity of multilingual image-text pairs. The speech modality overcomes this limitation due to its natural alignment with text and the abundance of existing speech datasets, which enable scalable language coverage. In this paper, we propose a Speech-guided Machine Translation (SMT) framework that integrates speech and text as fused inputs into an MLLM to improve translation quality. To mitigate reliance on low-resource data, we introduce a Self-Evolution Mechanism. The core components of this framework include a text-to-speech model, responsible for generating synthetic speech, and an MLLM capable of classifying synthetic speech samples and iteratively optimizing itself using positive samples. Experimental results demonstrate that our framework surpasses all existing methods on the Multi30K multimodal machine translation benchmark, achieving new state-of-the-art results. Furthermore, on general machine translation datasets, particularly the FLORES-200, it achieves average state-of-the-art performance in 108 translation directions. Ablation studies on CoVoST-2 confirms that differences between synthetic and authentic speech have negligible impact on translation quality. The code and models are released at https://github.com/yxduir/LLM-SRT.

For agents

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

get_harvested_code_for_paper("2602.21646")
get_code_for_paper("2602.21646")
have("2602.21646")

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

curl https://syntology.ai/api/ran/2602.21646.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.21646.svg)](https://syntology.ai/paper/2602.21646)

Connect an agent — have() is free.