Papers › IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for...

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

9 Oct 2024arXiv:2410.07171archive 2025-07-28

Xinchen Zhang, Ling Yang, Guohao Li, Yaqi Cai, Jiake Xie, Yong Tang, Yujiu Yang, Mengdi Wang, Bin Cui

Advanced diffusion models like RPG, Stable Diffusion 3 and FLUX have made notable strides in compositional text-to-image generation. However, these methods typically exhibit distinct strengths for compositional generation, with some excelling in handling attribute binding and others in spatial relationships. This disparity highlights the need for an approach that can leverage the complementary strengths of various models to comprehensively improve the composition capability. To this end, we introduce IterComp, a novel framework that aggregates composition-aware model preferences from multiple models and employs an iterative feedback learning approach to enhance compositional generation. Specifically, we curate a gallery of six powerful open-source diffusion models and evaluate their three key compositional metrics: attribute binding, spatial relationships, and non-spatial relationships. Based on these metrics, we develop a composition-aware model preference dataset comprising numerous image-rank pairs to train composition-aware reward models. Then, we propose an iterative feedback learning method to enhance compositionality in a closed-loop manner, enabling the progressive self-refinement of both the base diffusion model and reward models over multiple iterations. Theoretical proof demonstrates the effectiveness and extensive experiments show our significant superiority over previous SOTA methods (e.g., Omost and FLUX), particularly in multi-category object composition and complex semantic alignment. IterComp opens new research avenues in reward feedback learning for diffusion models and compositional generation. Code: https://github.com/YangLing0818/IterComp

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.

Syntology holds a reference implementation of IterComp, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='IterComp') (how to connect); the free check have('2410.07171') needs no token.

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

Code

Syntology 18 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 10 samples from 1 repository, 8 ran (4 with no instrument failure; 4 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 11 samples that ran have no recorded date.

yangling0818/itercomp officialmentioned in papermentioned on GitHubpytorchMITSyntology: 8 samples, 3 ran (1 instrument-failed) · 5 unverified report
yangling0818/rpg-diffusionmaster mentioned on GitHubpytorchMITSyntology: 10 samples, 8 ran (4 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

18 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 7 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.

2ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
2ran
7unverified

Licence: 3 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

yangling0818/itercomp official repository 8 samples, 3 ran (1 instrument-failed) · 5 unverified
is_url in 30 papers train/models/blip.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 4d1d9c47619920ba · report fixture: signature url_or_filename:str/0/str · returned bool · level recorded 2026-09-22
load in 392 papers Iterative_feedback/utils.py ran MIT (permissive) · 96b66ffedde07222 · report fixture: returned ImageReward · level recorded 2026-09-24
loss_func in 26 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
train/train_reward_models.py ran · our draft was wrong fingerprinted MIT (permissive) · 1164a205d991f3d8 · report fixture: signature reward:Tensor/2/float · returned tuple · level recorded, date not recorded
ImageReward_download Iterative_feedback/utils.py unverified MIT (permissive) · b1ae6f0bdf766e6c · report
encode_prompt_rm Iterative_feedback/feedback_train.py unverified MIT (permissive) · 2d955b94f1d7c1b6 · report
import_model_class_from_model_name_or_path in 64 papers Iterative_feedback/feedback_train.py unverified MIT (permissive) · 01e3b39e9e10abfb · report
load_score in 6 papers Iterative_feedback/utils.py unverified MIT (permissive) · ef6e5967acc37116 · report
parse_args in 355 papers Iterative_feedback/feedback_train.py unverified MIT (permissive) · 46770865c030e572 · report
yangling0818/rpg-diffusionmaster community (archive-listed) 10 samples, 8 ran (4 instrument-failed) · 2 unverified
floatdef matrix.py ran · honoured contract MIT (permissive) · 9b32f5c5fdc1fed6 · report fixture: signature x:str/0/str, vdef:float/0/float · returned float · level recorded 2026-09-24
get_params_dict mllm.py ran · our draft was wrong MIT (permissive) · 8a3533b6e18fc64e · report fixture: signature output_text:str/0/str · returned dict · level recorded 2026-09-24
is_l2 matrix.py ran · violated contract fingerprinted MIT (permissive) · 98feb4cf3a68bbf2 · report fixture: signature l:list/1/list · returned bool · level recorded 2026-09-24
l2_count matrix.py ran · honoured contract MIT (permissive) · 44c2fbeedf9741bb · report fixture: signature l:list/1/list · returned int · level recorded 2026-09-24
rescale_noise_cfg in 63 papers
census: 2 implementations from 21 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 4, kind float, dtype float32
RegionalDiffusion_base.py ran · our draft was wrong fingerprinted MIT (permissive) · bea2d776a332f2b0 · report fixture: signature noise_cfg:Tensor/4/float, noise_pred_text:Tensor/4/float, guidance_rescale:float/0/float · returned Tensor · level recorded, date not recorded
retrieve_timesteps in 70 papers RegionalDiffusion_xl.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 63e7d99da5ea137f · report fixture: signature scheduler:MockScheduler/0/?, num_inference_steps:int/0/int, device:str/0/str, timesteps:NoneType/0/? · returned tuple · level recorded, date not recorded
retrieve_timesteps in 70 papers RegionalDiffusion_base.py ran · our draft was wrong MIT (permissive) · 6cccd001a059f194 · report fixture: signature scheduler:MockScheduler/0/?, num_inference_steps:int/0/int, device:str/0/str, timesteps:NoneType/0/? · returned tuple · level recorded 2026-09-24
split_dims cross_attention.py ran MIT (permissive) here; the stored copy is pointer only · 56156523c6123e73 · report fixture: signature x_t:int/0/int, height:int/0/int, width:int/0/int, self:MinimalModule/0/? · returned tuple · level recorded 2026-09-26
GPT4 mllm.py unverified MIT (permissive) · 24399db18bc9c34f · report
local_llm mllm.py unverified MIT (permissive) · 0861ce73c0e98185 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

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

generated Assembly for IterComp (graph method: IterComp), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. reward_model_loss entry · level 3 · ran · honoured contract · 419a6758209f40cab1eb3f2084955f7fe3b16ed8dd931e16bcded577271af5d7

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="2410.07171") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AttributeImage GenerationText to Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASEDiffusion

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