SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.11273 · 2024

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 6 failures 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/2405.11273.json · badge: /api/ran/2405.11273.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
hitsz-tmg/umoe-scaling-unified-multimodal-llms canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni-MoE-2/decoder/models.py
pointer only (licence: NONE) · get_code("9fcdaa6e423e8aa7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/umoe-scaling-unified-multimodal-llms 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_vision_projector Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni_MoE/Uni_MoE_audio/model/multimodal_projector/builder.py
pointer only (licence: NONE) · get_code("ef4db0da176c674c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/umoe-scaling-unified-multimodal-llms 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.

nonlinearity Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni-MoE-2/decoder/models.py
pointer only (licence: NONE) · get_code("3137073275f8c21a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/umoe-scaling-unified-multimodal-llms 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.

safe_log Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni-MoE-2/decoder/modules.py
pointer only (licence: NONE) · get_code("5923f41e711c0b69")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/umoe-scaling-unified-multimodal-llms 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.

symexp Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni-MoE-2/decoder/modules.py
pointer only (licence: NONE) · get_code("f1abe87534e9b4b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/umoe-scaling-unified-multimodal-llms 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.

symlog Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni-MoE-2/decoder/modules.py
pointer only (licence: NONE) · get_code("3acb919a94ac1a19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/umoe-scaling-unified-multimodal-llms 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_vision_tower Not yet run
unverified (harvested, no recorded run)
hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni_MoE/Uni_MoE_audio/model/multimodal_encoder/builder.py
pointer only (licence: NONE); the stored copy get_code serves, from AuroraZengfh/ModalPrompt, is pointer only (licence: NONE) · get_code("9d8ae430eef240b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/umoe-scaling-unified-multimodal-llms 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.

make_attn Not yet run
unverified (harvested, no recorded run)
hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni-MoE-2/decoder/models.py
pointer only (licence: NONE) · get_code("dba3d5f0d0d4a6f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/umoe-scaling-unified-multimodal-llms 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 8 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 4 the same month, 8 later) and 0 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
nonlinearity 156 other papers
77 dated earlier, 4 the same month, 71 later, 4 same year, order not determinable · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
Normalize 54 other papers
23 dated earlier, 1 the same month, 29 later, 1 same year, order not determinable · 3 only as an assembly brick
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2208.13753 (2022-08)
Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis
2211.13221 (2022-11)
Latent Video Diffusion Models for High-Fidelity Long Video Generation
and 51 more not named here
build_vision_projector 17 other papers
4 dated earlier, 1 the same month, 12 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
build_vision_tower 9 other papers
4 dated earlier, 1 the same month, 4 later · 4 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
2402.11684 (2024-02)
ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models
and 6 more not named here
safe_log 5 other papers
2 dated earlier, 3 later
2306.00814 (2023-06)
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
2402.12208 (2024-02)
Language-Codec: Bridging Discrete Codec Representations and Speech Language Models
2407.05361 (2024-07)
Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
and 2 more not named here
symexp 5 other papers
2 dated earlier, 3 later
2306.00814 (2023-06)
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
2402.12208 (2024-02)
Language-Codec: Bridging Discrete Codec Representations and Speech Language Models
2407.05361 (2024-07)
Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
and 2 more not named here
symlog 5 other papers
2 dated earlier, 3 later
2306.00814 (2023-06)
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
2402.12208 (2024-02)
Language-Codec: Bridging Discrete Codec Representations and Speech Language Models
2407.05361 (2024-07)
Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
and 2 more not named here
make_attn 1 other paper
1 later
2408.16532 (2024-08)
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

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

Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE) architecture has been employed to efficiently scale large language and image-text models, these efforts typically involve fewer experts and limited modalities. To address this, our work presents the pioneering attempt to develop a unified MLLM with the MoE architecture, named Uni-MoE that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We also implement a sparse MoE architecture within the LLMs to enable efficient training and inference through modality-level data parallelism and expert-level model parallelism. To enhance the multi-expert collaboration and generalization, we present a progressive training strategy: 1) Cross-modality alignment using various connectors with different cross-modality data, 2) Training modality-specific experts with cross-modality instruction data to activate experts' preferences, and 3) Tuning the Uni-MoE framework utilizing Low-Rank Adaptation (LoRA) on mixed multimodal instruction data. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets. The extensive experimental results demonstrate Uni-MoE's principal advantage of significantly reducing performance bias in handling mixed multimodal datasets, alongside improved multi-expert collaboration and generalization. Our findings highlight the substantial potential of MoE frameworks in advancing MLLMs and the code is available at https://github.com/HITsz-TMG/UMOE-Scaling-Unified-Multimodal-LLMs.

For agents

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

get_harvested_code_for_paper("2405.11273")
get_code_for_paper("2405.11273")
have("2405.11273")

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

curl https://syntology.ai/api/ran/2405.11273.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.11273.svg)](https://syntology.ai/paper/2405.11273)

Connect an agent — have() is free.