Papers › ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

2 Apr 2025arXiv:2504.01934archive 2025-07-28

Runhui Huang, Chunwei Wang, Junwei Yang, Guansong Lu, Yunlong Yuan, Jianhua Han, Lu Hou, Wei zhang, Lanqing Hong, Hengshuang Zhao, Hang Xu

We present ILLUME+ that leverages dual visual tokenization and a diffusion decoder to improve both deep semantic understanding and high-fidelity image generation. Existing unified models have struggled to simultaneously handle the three fundamental capabilities in a unified model: understanding, generation, and editing. Models like Chameleon and EMU3 utilize VQGAN for image discretization, due to the lack of deep semantic interaction, they lag behind specialist models like LLaVA in visual understanding tasks. To mitigate this, LaViT and ILLUME employ semantic encoders for tokenization, but they struggle with image editing due to poor texture preservation. Meanwhile, Janus series decouples the input and output image representation, limiting their abilities to seamlessly handle interleaved image-text understanding and generation. In contrast, ILLUME+ introduces a unified dual visual tokenizer, DualViTok, which preserves both fine-grained textures and text-aligned semantics while enabling a coarse-to-fine image representation strategy for multimodal understanding and generation. Additionally, we employ a diffusion model as the image detokenizer for enhanced generation quality and efficient super-resolution. ILLUME+ follows a continuous-input, discrete-output scheme within the unified MLLM and adopts a progressive training procedure that supports dynamic resolution across the vision tokenizer, MLLM, and diffusion decoder. This design allows for flexible and efficient context-aware image editing and generation across diverse tasks. ILLUME+ (3B) exhibits competitive performance against existing unified MLLMs and specialized models across multimodal understanding, generation, and editing benchmarks. With its strong performance, ILLUME+ provides a scalable and versatile foundation for future multimodal applications. Project Page: https://illume-unified-mllm.github.io/.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 1 repository, 19 ran (16 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 19 samples that ran has no recorded date.

illume-unified-mllm/ILLUME_plus mentioned on GitHubpytorchApache-2.0Syntology: 20 samples, 19 ran (3 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
15ran
1unverified

Licence: 0 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from illume-unified-mllm/ILLUME_plus. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

illume-unified-mllm/ILLUME_plus community (archive-listed) 20 samples, 19 ran (3 instrument-failed) · 1 unverified
all_gather in 119 papers ILLUME/illume/dist_utils.py ran Apache-2.0 (permissive) · 1c8d976c39a57c9e · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-25
calculate_image_token_num ILLUME/generation_eval/models/inference_utils.py ran Apache-2.0 (permissive) · d953291e013c1472 · report fixture: signature h:int/0/int, w:int/0/int, downsample_rate_per_level:list/1/int · returned tuple · level recorded 2026-09-25
check_image_token_num ILLUME/app_hf.py ran Apache-2.0 (permissive) · c255b91c2246dc37 · report fixture: signature image_embed_inds:list/1/list, token_nums:list/1/int, identifier:str/0/str · returned list · level recorded 2026-09-24
divide_to_patches in 65 papers ILLUME/illume/mm_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 7e03b180fa317c9a · report fixture: signature image:Image/0/?, patch_size:int/0/int · returned list · level recorded 2026-09-24
get_local_proc_group ILLUME/illume/dist_utils.py ran Apache-2.0 (permissive) · 4e189d5dad79f682 · report fixture: signature group_size:int/0/int · returned int · level recorded 2026-09-25
is_zero3_model ILLUME/illume/model/utils.py ran Apache-2.0 (permissive) · c55a1f7e4549fb3e · report fixture: signature model:callable/0/?, params:NoneType/0/? · returned bool · level recorded 2026-09-24
load_and_merge_config ILLUME/illume/registry_utils.py ran Apache-2.0 (permissive) · 9778219ab71b8d25 · report fixture: signature config_path:str/0/str · returned dict · level recorded 2026-09-24
load_py_config ILLUME/illume/registry_utils.py ran Apache-2.0 (permissive) · 3e40955600cc6631 · report fixture: signature config_path:str/0/str · returned dict · level recorded 2026-09-25
merge_dicts in 14 papers ILLUME/illume/registry_utils.py ran Apache-2.0 (permissive) · 10f7276899092b15 · report fixture: signature base:dict/0/?, new:dict/0/? · returned dict · level recorded 2026-09-25
pad_sequence in 46 papers ILLUME/app_hf.py ran Apache-2.0 (permissive) · d4d72d2f8ec8ae97 · report fixture: signature tokenizer:MockTokenizer/0/?, input_ids:list/1/Tensor, batch_first:bool/0/bool, padding_value:int/0/int · returned Tensor · level recorded 2026-09-24
pad_sequence in 46 papers ILLUME/generation_eval/models/illume.py ran Apache-2.0 (permissive) · 0a6a1f6fb96cd47b · report fixture: signature tokenizer:MockTokenizer/0/?, input_ids:list/1/Tensor, batch_first:bool/0/bool, padding_value:int/0/int · returned Tensor · level recorded 2026-09-25
parse_interleaved_text_image ILLUME/generation_eval/models/inference_utils.py ran Apache-2.0 (permissive) · c6ccde0b6ee512a0 · report fixture: signature full_output_text:str/0/str, num_levels:int/0/int, image_placeholder:str/0/str, start_tag:str/0/str, end_tag:str/0/str · returned tuple · level recorded 2026-09-24
reduce_dict in 73 papers ILLUME/illume/dist_utils.py ran · violated contract Apache-2.0 (permissive) · 2a3280757ce5a198 · report fixture: signature input_dict:dict/0/?, average:bool/0/bool · returned dict · level recorded 2026-09-22
replace_last ILLUME/illume/conversation.py ran fingerprinted Apache-2.0 (permissive) · d40f1727de55b957 · report fixture: signature original_string:str/0/str, target:str/0/str, replacement:str/0/str · returned str · level recorded 2026-09-25
replace_ratio_tags_in_text ILLUME/illume/conversation.py ran fingerprinted Apache-2.0 (permissive) · 25c22c3cf79f39b6 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
replace_sequentially_regex ILLUME/illume/conversation.py ran fingerprinted Apache-2.0 (permissive) · 4e41538bc082c01f · report fixture: signature original_string:str/0/str, target:str/0/str, content_list:list/1/str · returned str · level recorded 2026-09-25
resize_and_pad_image in 70 papers ILLUME/illume/mm_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 468eedeba67f1b00 · report fixture: signature image:Image/0/?, target_resolution:tuple/1/int · returned Image · level recorded 2026-09-24
select_best_resolution in 71 papers ILLUME/illume/mm_utils.py ran Apache-2.0 (permissive) · 29d67c6717548a53 · report fixture: signature original_size:tuple/1/int, possible_resolutions:list/1/tuple · returned tuple · level recorded 2026-09-25
unpad_image in 72 papers
census: 4 implementations from 34 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 3, kind float, dtype float32
ILLUME/illume/model/illume_arch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 55c32993da87759b · report fixture: signature tensor:Tensor/3/float, original_size:tuple/1/int · returned Tensor · level recorded, date not recorded
load_state_dict_maybe_zero_3 ILLUME/illume/model/utils.py unverified Apache-2.0 (permissive) · 14dac797f0c4b233 · report

Tasks

DecoderImage GenerationImage ReconstructionSuper-ResolutionText-based Image EditingVisual Question Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections