SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.08265 · ICML · 2024

A Dense Reward View on Aligning Text-to-Image Diffusion with Preference

Mingyuan Zhou, Tianqi Chen, Shentao Yang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 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/2402.08265.json · badge: /api/ran/2402.08265.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
shentao-yang/dense_reward_t2i canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
concat_imgs Ran
ran; our contract draft was wrong, not the code
shentao-yang/dense_reward_t2i/eval_ckpts/stable_diffusion_pipeline_traj.py
pointer only (licence: NONE) · get_code("c489bb9ff3f10f97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shentao-yang/dense_reward_t2i 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.

get_snr_schedule Ran
ran, honoured the contract we drafted
shentao-yang/dense_reward_t2i/utils.py
pointer only (licence: NONE) · get_code("244e50dfe922e639")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shentao-yang/dense_reward_t2i 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.

listMLELoss Ran
ran; our contract draft was wrong, not the code
shentao-yang/dense_reward_t2i/reward_loss.py
pointer only (licence: NONE) · get_code("6ab46c06e144019b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shentao-yang/dense_reward_t2i 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.

make_banner Ran
ran; our contract draft was wrong, not the code
shentao-yang/dense_reward_t2i/utils.py
pointer only (licence: NONE) · get_code("88fc4c03f1a33d44")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shentao-yang/dense_reward_t2i 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.

register_score Ran
ran; our contract draft was wrong, not the code
shentao-yang/dense_reward_t2i/scorer_ensemble.py
pointer only (licence: NONE) · get_code("4bd02a478fc9cfdf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shentao-yang/dense_reward_t2i 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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.

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

Aligning text-to-image diffusion model (T2I) with preference has been gaining increasing research attention. While prior works exist on directly optimizing T2I by preference data, these methods are developed under the bandit assumption of a latent reward on the entire diffusion reverse chain, while ignoring the sequential nature of the generation process. This may harm the efficacy and efficiency of preference alignment. In this paper, we take on a finer dense reward perspective and derive a tractable alignment objective that emphasizes the initial steps of the T2I reverse chain. In particular, we introduce temporal discounting into DPO-style explicit-rewardfree objectives, to break the temporal symmetry therein and suit the T2I generation hierarchy. In experiments on single and multiple prompt generation, our method is competitive with strong relevant baselines, both quantitatively and qualitatively. Further investigations are conducted to illustrate the insight of our approach. Source code is available at https://github.com/ Shentao-YANG/Dense_Reward_T2I .

For agents

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

get_harvested_code_for_paper("2402.08265")
get_code_for_paper("2402.08265")
have("2402.08265")

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

curl https://syntology.ai/api/ran/2402.08265.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.08265.svg)](https://syntology.ai/paper/2402.08265)

Connect an agent — have() is free.