Papers › GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with...

GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning

22 May 2025arXiv:2505.17022archive 2025-07-28

Chengqi Duan, Rongyao Fang, Yuqing Wang, Kun Wang, Linjiang Huang, Xingyu Zeng, Hongsheng Li, Xihui Liu

Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of such prompts requires explicit reasoning about the semantic content and spatial layout. We present GoT-R1, a framework that applies reinforcement learning to enhance semantic-spatial reasoning in visual generation. Building upon the Generation Chain-of-Thought approach, GoT-R1 enables models to autonomously discover effective reasoning strategies beyond predefined templates through carefully designed reinforcement learning. To achieve this, we propose a dual-stage multi-dimensional reward framework that leverages MLLMs to evaluate both the reasoning process and final output, enabling effective supervision across the entire generation pipeline. The reward system assesses semantic alignment, spatial accuracy, and visual quality in a unified approach. Experimental results demonstrate significant improvements on T2I-CompBench benchmark, particularly in compositional tasks involving precise spatial relationships and attribute binding. GoT-R1 advances the state-of-the-art in image generation by successfully transferring sophisticated reasoning capabilities to the visual generation domain. To facilitate future research, we make our code and pretrained models publicly available at https://github.com/gogoduan/GoT-R1.

PaperPDFCodeCode Syntology ranMethod as code

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 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 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: official repository: 11 samples from 1 repository, 9 ran (7 with no instrument failure; 2 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

gogoduan/got-r1 officialmentioned in papermentioned on GitHubpytorchSyntology: 11 samples, 9 ran (2 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

11 samples harvested: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 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 has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
1ran; the contract check could not run
7ran
2unverified

Licence: 11 of the 11 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 gogoduan/got-r1. “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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

gogoduan/got-r1 official repository 11 samples, 9 ran (2 instrument-failed) · 2 unverified
Decoder in 210 papers src/models/vq_model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 71736837a54c2c84 · report fixture: returned Decoder · level recorded 2026-09-22
Downsample in 58 papers src/models/vq_model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 6618daf64230cf0c · report fixture: returned Downsample · level recorded 2026-09-22
Encoder in 278 papers src/models/vq_model.py ran · metamorphic tier: deterministic no licence file found · pointer only · eed2973632740358 · report fixture: returned Encoder · level recorded 2026-09-22
ModelArgs in 13 papers src/models/vq_model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 51c13049b5aebe83 · report fixture: returned ModelArgs · level recorded 2026-09-22
Normalize in 154 papers src/models/vq_model.py ran · our draft was wrong no licence file found · pointer only · 01b5cf639b6bac89 · report fixture: signature in_channels:int/0/int, norm_type:str/0/str · returned GroupNorm · level recorded 2026-09-22
ResnetBlock in 49 papers src/models/vq_model.py ran no licence file found · pointer only · b9580b7064989831 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Upsample in 77 papers src/models/vq_model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 6687b2b39ca9fecc · report fixture: returned Upsample · level recorded 2026-09-22
VectorQuantizer in 26 papers src/models/vq_model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 177a67c6ea19650c · report fixture: returned VectorQuantizer · level recorded 2026-09-22
compute_entropy_loss in 20 papers
census: 5 implementations from 11 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32
src/models/vq_model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 774c95b77d7621f3 · report fixture: signature affinity:Tensor/3/float, loss_type:str/0/str, temperature:float/0/float · returned Tensor · level recorded 2026-09-22
AttnBlock in 22 papers src/models/vq_model.py unverified no licence file found · pointer only · 93ec039f4b98caf7 · report
VQModel src/models/vq_model.py unverified no licence file found · pointer only · 5cb4851ddaa665bf · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for GoT-R1 (graph method: GoT-R1). 12 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. VQModel entry · level 0 · unverified · 5cb4851ddaa665bf
  2. Decoder model · level 1 · ran · 71736837a54c2c84
  3. Encoder model · level 1 · ran · eed2973632740358
  4. ModelArgs helper · level 1 · ran · 51c13049b5aebe83
  5. VectorQuantizer model · level 1 · ran · 177a67c6ea19650c
  6. AttnBlock model · level 0 · unverified · 93ec039f4b98caf7
  7. Normalize helper · level 1 · ran · our draft was wrong · 01b5cf639b6bac89
  8. ResnetBlock model · level 1 · ran · b9580b7064989831
  9. Upsample model · level 1 · ran · 6687b2b39ca9fecc
  10. nonlinearity helper · level 1 · ran · our draft was wrong · 3137073275f8c21a
  11. Downsample model · level 1 · ran · 6618daf64230cf0c
  12. compute_entropy_loss loss · level 1 · ran; the contract check could not run (RAISES) · 774c95b77d7621f3

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2505.17022") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AttributeImage GenerationReinforcement LearningSpatial Reasoningreinforcement-learning

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