Papers › Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline...

Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning

25 Apr 2023arXiv:2304.12824archive 2025-07-28

Cheng Lu, Huayu Chen, Jianfei Chen, Hang Su, Chongxuan Li, Jun Zhu

Guided sampling is a vital approach for applying diffusion models in real-world tasks that embeds human-defined guidance during the sampling procedure. This paper considers a general setting where the guidance is defined by an (unnormalized) energy function. The main challenge for this setting is that the intermediate guidance during the diffusion sampling procedure, which is jointly defined by the sampling distribution and the energy function, is unknown and is hard to estimate. To address this challenge, we propose an exact formulation of the intermediate guidance as well as a novel training objective named contrastive energy prediction (CEP) to learn the exact guidance. Our method is guaranteed to converge to the exact guidance under unlimited model capacity and data samples, while previous methods can not. We demonstrate the effectiveness of our method by applying it to offline reinforcement learning (RL). Extensive experiments on D4RL benchmarks demonstrate that our method outperforms existing state-of-the-art algorithms. We also provide some examples of applying CEP for image synthesis to demonstrate the scalability of CEP on high-dimensional data.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2304.12824")

Code

Syntology Ran 17 of 27 code samples harvested from 3 repositories linked to this paper; 10 have no recorded run. Of those that ran: 3 ran · honoured contract; 5 ran · our draft was wrong; 1 ran · fixture could not drive it; 8 ran with no contract checked.

By repository: official repository: 21 samples from 1 repository, 13 ran; community (archive-listed): 6 samples from 2 repositories, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

thu-ml/cep-energy-guided-diffusion officialmentioned in papermentioned on GitHubpytorchMIT report
chendrag/sfbc mentioned on GitHubpytorch report
opendilab/DI-engine mentioned on GitHubpytorch 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

27 samples harvested; 17 ran; 3 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
5ran · our draft was wrong
1ran · fixture could not drive it
8ran
10unverified

Licence: 5 of the 27 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

center_crop_arr thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/image_datasets.py official repository ran · our draft was wrong MIT (permissive) · 8ab9a97df8161f31 · report
approx_standard_normal_cdf thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/losses.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · cfd76fd0d89574a4 · report
betas_for_alpha_bar thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/gaussian_diffusion.py official repository ran · honoured contract MIT (permissive) · 2ab2316ac6fdd869 · report
create_named_schedule_sampler thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/resample.py official repository ran · our draft was wrong MIT (permissive) · 35572566acf61c78 · report
discretized_gaussian_log_likelihood thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/losses.py official repository ran · our draft was wrong MIT (permissive) · cd33283d615fb3d7 · report
get_named_beta_schedule thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/gaussian_diffusion.py official repository ran · honoured contract MIT (permissive) · a086d6286a40b889 · report
get_param_groups_and_shapes thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/fp16_util.py official repository ran MIT (permissive) · e41367ad14ff58fd · report
make_master_params thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/fp16_util.py official repository ran MIT (permissive) · e20dd5102da3b050 · report
make_output_format thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/logger.py official repository ran MIT (permissive) · bcd8b4acab199405 · report
normal_kl thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/losses.py official repository ran · honoured contract fingerprinted MIT (permissive) · cf2798b666b231ca · report
space_timesteps thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/respace.py official repository ran · fixture could not drive it MIT (permissive) · 9b6e4e070473e76f · report
unflatten_master_params thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/fp16_util.py official repository ran MIT (permissive) · 64fff1e30802b815 · report
zero_module thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/new.py official repository ran · our draft was wrong MIT (permissive) · 129b804760b3115f · report
avg_pool_nd thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/new.py official repository unverified MIT (permissive) · ecd0fc28815b65ae · report
conv_nd thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/new.py official repository unverified MIT (permissive) · fe4eb545bbb728e0 · report
create_classifier_and_diffusion thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/script_util.py official repository unverified MIT (permissive) · 5e5d99a81705a07f · report
create_model thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/script_util.py official repository unverified MIT (permissive) · 35ea054532112e53 · report
create_model_and_diffusion thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/script_util.py official repository unverified MIT (permissive) · 6a3cfc58dafbe392 · report
mpi_weighted_mean thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/logger.py official repository unverified MIT (permissive) · e515a67f7f32e76d · report
profile thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/logger.py official repository unverified MIT (permissive) · 0c6607473a4c4c55 · report
random_crop_arr thu-ml/cep-energy-guided-diffusion/images/guided_diffusion/image_datasets.py official repository unverified MIT (permissive) · 53d5be4fdbcfac23 · report
ContrastiveLoss opendilab/DI-engine/ding/torch_utils/loss/contrastive_loss.py community (archive-listed) ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a58c4f9c165debe0 · report
GaussianFourierProjection chendrag/sfbc/diffusion_SDE/model.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 08efd796ca31c61d · report
MUlQnet chendrag/sfbc/diffusion_SDE/model.py community (archive-listed) ran · metamorphic tier: invariant no licence file found · pointer only · d46234d5c330655a · report
MlpQnet chendrag/sfbc/diffusion_SDE/model.py community (archive-listed) ran · metamorphic tier: invariant no licence file found · pointer only · 0dea05ba16fe2e4b · report
ScoreBase chendrag/sfbc/diffusion_SDE/model.py community (archive-listed) unverified no licence file found · pointer only · 2a016b24a089f7d2 · report
ScoreNet chendrag/sfbc/diffusion_SDE/model.py community (archive-listed) unverified no licence file found · pointer only · 9ccfba3c00a175f6 · report

Tasks

D4RLImage GenerationReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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