Papers › UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

29 May 2025arXiv:2505.23380archive 2025-07-28

Weijia Mao, Zhenheng Yang, Mike Zheng Shou

Unified multimodal large language models such as Show-o and Janus have achieved strong performance across both generation and understanding tasks. However, these models typically rely on large-scale datasets and require substantial computation during the pretraining stage. In addition, several post-training methods have been proposed, but they often depend on external data or are limited to task-specific customization. In this work, we introduce UniRL, a self-improving post-training approach. Our approach enables the model to generate images from prompts and use them as training data in each iteration, without relying on any external image data. Moreover, it enables the two tasks to enhance each other: the generated images are used for understanding, and the understanding results are used to supervise generation. We explore supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) to optimize the models. UniRL offers three key advantages: (1) it requires no external image data, as all training samples are generated by the model itself during training; (2) it not only improves individual task performance, but also reduces the imbalance between generation and understanding; and (3) it requires only several additional training steps during the post-training stage. We evaluate UniRL on top of Show-o and Janus, achieving a GenEval score of 0.77 for Show-o and 0.65 for Janus. Code and models will be released in https://github.com/showlab/UniRL.

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 12 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 10 ran (2 with no instrument failure; 8 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. 3 of the 10 samples that ran have no recorded date.

showlab/unirl officialmentioned in paperjaxApache-2.0Syntology: 12 samples, 10 ran (8 instrument-failed) · 2 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

12 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 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.

8ran · our draft was wrong
2ran
2unverified

Licence: 6 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from showlab/unirl. “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.

showlab/unirl official repository 12 samples, 10 ran (8 instrument-failed) · 2 unverified
Normalize in 154 papers models/common_modules.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · c3a6b977022957cb · report fixture: signature in_channels:int/0/int · returned GroupNorm · level recorded, date not recorded
compute_iou in 68 papers evaluate_imgs.py ran fingerprinted Apache-2.0 (permissive) · 2f96ce289cb03a29 · report fixture: signature box_a:list/1/int, box_b:list/1/int · returned float · level recorded 2026-09-25
flatten_omega_conf inference.py ran Apache-2.0 (permissive) · d15d620fa9ed83c7 · report fixture: signature cfg:DictConfig/0/?, resolve:bool/0/bool · returned list · level recorded 2026-09-25
get_constant_schedule in 21 papers models/lr_schedulers.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · a8366f238618edad · report fixture: signature optimizer:SGD/0/?, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
get_constant_schedule_with_warmup in 25 papers models/lr_schedulers.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 11f07821d1b2286b · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
get_linear_schedule_with_warmup in 39 papers models/lr_schedulers.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 1975e0c51e6f5753 · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/common_modules.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
soft_target_cross_entropy inference.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d8437c41cc2a860f · report fixture: signature logits:Tensor/3/float, targets:Tensor/2/int, soft_targets:Tensor/3/float · returned Tensor · level recorded, date not recorded
timed in 10 papers evaluate_imgs.py ran · our draft was wrong Apache-2.0 (permissive) · 844a4aecea80d106 · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-22
unpack_time in 7 papers models/common_modules.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 2d82abbef2c4addb · report fixture: signature t:Tensor/4/float, batch:int/0/int · returned Tensor · level recorded 2026-09-24
get_logger in 383 papers models/logging.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 376bf22d5737fc2a · report
get_vq_model_class inference.py unverified Apache-2.0 (permissive) · 509a71c867af544b · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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