SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.09024 · NeurIPS · 2024

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control

Hang Su, Jun Zhu, Kaiwen Zheng, Huayu Chen

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 4 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-21; 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/2407.09024.json · badge: /api/ran/2407.09024.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
thu-ml/Efficient-Diffusion-Alignment canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
thu-ml/efficient-diffusion-alignment canonical (classifier label)
classifier basis: classifier_2025
0 ran · 4 no recorded run
FunctionStatusWhere it lives
interpolate_fn Ran
ran; our contract draft was wrong, not the code
thu-ml/Efficient-Diffusion-Alignment/dpm_solver_pytorch.py
pointer only (licence: NONE) · get_code("6a35b62fbc80f70a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/Efficient-Diffusion-Alignment 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.

asymmetric_l2_loss Ran
ran; our contract draft was wrong, not the code
thu-ml/Efficient-Diffusion-Alignment/BDiffusion.py
pointer only (licence: NONE) · get_code("579d77f78c03773e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/Efficient-Diffusion-Alignment 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.

expand_dims Ran
ran; our contract draft was wrong, not the code
thu-ml/Efficient-Diffusion-Alignment/dpm_solver_pytorch.py
pointer only (licence: NONE) · get_code("e6110366588c5c65")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/Efficient-Diffusion-Alignment 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.

inf_train_gen Ran
ran; our contract draft was wrong, not the code
thu-ml/Efficient-Diffusion-Alignment/dataset.py
pointer only (licence: NONE) · get_code("c8b1ea2dbf064b81")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/Efficient-Diffusion-Alignment 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.

marginal_prob_std Ran
ran, honoured the contract we drafted
thu-ml/Efficient-Diffusion-Alignment/utils.py
pointer only (licence: NONE) · get_code("057c095634d04249")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/Efficient-Diffusion-Alignment 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.

mlp Ran
ran; our contract draft was wrong, not the code
thu-ml/Efficient-Diffusion-Alignment/model.py
pointer only (licence: NONE); the stored copy get_code serves, from liamyzq/Doob_training_free_adaptation, is pointer only (licence: NONE) · get_code("d466e7f1c4364a0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/Efficient-Diffusion-Alignment 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.

model_wrapper Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thu-ml/Efficient-Diffusion-Alignment/dpm_solver_pytorch.py
pointer only (licence: NONE); the stored copy get_code serves, from wl-zhao/dc-solver, is pointer only (licence: NONE) · get_code("c38c4cd486f7a766")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/Efficient-Diffusion-Alignment 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.

return_range Ran
ran, honoured the contract we drafted
thu-ml/Efficient-Diffusion-Alignment/dataset.py
pointer only (licence: NONE) · get_code("732209d369d824c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/Efficient-Diffusion-Alignment 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.

CEP_Critic Not yet run
unverified (harvested, no recorded run)
thu-ml/efficient-diffusion-alignment/BDiffusion.py
pointer only (licence: NONE) · get_code("3a044b5fa091a33b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/efficient-diffusion-alignment 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. No invocation recorded.

EDA_policy Not yet run
unverified (harvested, no recorded run)
thu-ml/efficient-diffusion-alignment/BDiffusion.py
pointer only (licence: NONE) · get_code("8f226f7f0a3a49f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/efficient-diffusion-alignment 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. No invocation recorded.

IQL_Critic Not yet run
unverified (harvested, no recorded run)
thu-ml/efficient-diffusion-alignment/BDiffusion.py
pointer only (licence: NONE) · get_code("b9ad37c17cb01b28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/efficient-diffusion-alignment 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. No invocation recorded.

update_target Not yet run
unverified (harvested, no recorded run)
thu-ml/efficient-diffusion-alignment/BDiffusion.py
pointer only (licence: NONE) · get_code("5e582540e0a940ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/efficient-diffusion-alignment 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 1 the same month, 8 later) and 3 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.

FunctionAlso present inEarliest-datedOthers named
expand_dims 39 other papers
23 dated earlier, 13 later, 3 same year, order not determinable · 4 only as an assembly brick
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2202.09778 (2022-02)
Pseudo Numerical Methods for Diffusion Models on Manifolds
2206.00927 (2022-06)
DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
and 36 more not named here
interpolate_fn 34 other papers
20 dated earlier, 1 the same month, 10 later, 3 same year, order not determinable
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2211.01095 (2022-11)
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
2212.09478 (2022-12)
MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation
and 31 more not named here
asymmetric_l2_loss
brick of this paper's assembly: helper
6 other papers
3 dated earlier, 3 later · 2 only as an assembly brick
2110.06169 (2021-10)
Offline Reinforcement Learning with Implicit Q-Learning
2210.08323 (2022-10)
A Policy-Guided Imitation Approach for Offline Reinforcement Learning
2310.07297 (2023-10)
Score Regularized Policy Optimization through Diffusion Behavior
and 3 more not named here
model_wrapper 6 other papers
3 dated earlier, 2 later, 1 same year, order not determinable
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
aaai_28147 (2024 (year only))
Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model
2401.11708 (2024-01)
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
and 3 more not named here
mlp 2 other papers
2 later
2602.16198 (2026-02)
Training-Free Adaptation of Diffusion Models via Doob's h-Transform
2608.02332 (2026-08)
Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning
update_target
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later · 2 only as an assembly brick
2310.07297 (2023-10)
Score Regularized Policy Optimization through Diffusion Behavior
2602.16198 (2026-02)
Training-Free Adaptation of Diffusion Models via Doob's h-Transform
IQL_Critic
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2310.07297 (2023-10)
Score Regularized Policy Optimization through Diffusion Behavior
marginal_prob_std 1 other paper
1 later
2608.02332 (2026-08)
Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning
return_range 1 other paper
1 later
2608.02332 (2026-08)
Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes diffusion models for behavior modeling. However, unlike previous approaches, we represent diffusion policies as the derivative of a scalar neural network with respect to action inputs. This representation is critical because it enables direct density calculation for diffusion models, making them compatible with existing LLM alignment theories. During policy fine-tuning, we extend preference-based alignment methods like Direct Preference Optimization (DPO) to align diffusion behaviors with continuous Q-functions. Our evaluation on the D4RL benchmark shows that EDA exceeds all baseline methods in overall performance. Notably, EDA maintains about 95% of performance and still outperforms several baselines given only 1% of Q-labelled data during fine-tuning. Code: https://github.com/thu-ml/Efficient-Diffusion-Alignment Recent advances in Large Language Model (LLM) alignment techniques [57,37,43] offer valuable insights for fine-tuning diffusion behavior policies due to the fundamental similarity of the issues they aim to address (Fig. 1). While pretrained LLMs accurately imitate language patterns from web-scale corpus, they also capture toxic or unwanted content within the dataset. Alignment algorithms, such as Direct Preference Optimization (DPO, [41]), are designed to remove harmful or useless content learned during pretraining. They enable quick adaptations of pretrained LLMs to human intentions * The corresponding author. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).

For agents

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

get_harvested_code_for_paper("2407.09024")
get_code_for_paper("2407.09024")
have("2407.09024")

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

curl https://syntology.ai/api/ran/2407.09024.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.09024.svg)](https://syntology.ai/paper/2407.09024)

Connect an agent — have() is free.