Papers › Energy Transformer

Energy Transformer

14 Feb 2023NeurIPS 2023 11arXiv:2302.07253archive 2025-07-28

Benjamin Hoover, Yuchen Liang, Bao Pham, Rameswar Panda, Hendrik Strobelt, Duen Horng Chau, Mohammed J. Zaki, Dmitry Krotov

Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory. Attention is the power-house driving modern deep learning successes, but it lacks clear theoretical foundations. Energy-based models allow a principled approach to discriminative and generative tasks, but the design of the energy functional is not straightforward. At the same time, Dense Associative Memory models or Modern Hopfield Networks have a well-established theoretical foundation, and allow an intuitive design of the energy function. We propose a novel architecture, called the Energy Transformer (or ET for short), that uses a sequence of attention layers that are purposely designed to minimize a specifically engineered energy function, which is responsible for representing the relationships between the tokens. In this work, we introduce the theoretical foundations of ET, explore its empirical capabilities using the image completion task, and obtain strong quantitative results on the graph anomaly detection and graph classification tasks.

PaperPDFConference PDFCodeCode Syntology ran

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 13 code samples: 11 from 4 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 13: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 4 repositories, 11 ran (7 with no instrument failure; 4 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 13 samples that ran has no recorded date.

bhoov/energy-transformer-jax officialmentioned in papermentioned on GitHubjaxSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
zhuergou/energy-transformer-for-graph-anomaly-detection officialmentioned in paperpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Lemon-cmd/energy-transformer-graph officialmentioned on GitHubjaxSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
Lemon-cmd/energy-transformer-torch officialmentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 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

13 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 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.

2ran · honoured contract
4ran · our draft was wrong
2ran; the contract check could not run
5ran

Licence: 3 of the 13 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 4 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. 2 samples are listed last, in a group without a repository. “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.

bhoov/energy-transformer-jax official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
array_to_img image_core.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 75dcdb1c3263beb4 · report fixture: signature x:ndarray/3/float · returned ndarray · level recorded 2026-09-22
img_to_array image_core.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 43e7507240634b11 · report fixture: signature im:ndarray/3/int · returned ndarray · level recorded 2026-09-22
zhuergou/energy-transformer-for-graph-anomaly-detection official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
custom_message_func energy_transformer_layer.py ran · our draft was wrong no licence file found · pointer only · e232328a8a2b8b09 · report fixture: signature src_f1_field:str/0/str, edge_field:str/0/str, out_field:str/0/str, src_f2_field:str/0/str · returned function · level recorded 2026-09-22
Lemon-cmd/energy-transformer-graph official repository 2 samples, 2 ran (1 instrument-failed) · 0 unverified
check_type in 6 papers src/model/et.py ran · honoured contract MIT (permissive) · 9f8fb6db436eff3e · report fixture: signature x:ArrayImpl/1/float · returned int · level recorded 2026-09-22
normal in 11 papers src/model/et.py ran · our draft was wrong MIT (permissive) · d67b0a557c3733b2 · report fixture: signature key:ArrayImpl/1/int, shape:tuple/1/int, mean:float/0/float, std:float/0/float · returned ArrayImpl · level recorded 2026-09-22
Lemon-cmd/energy-transformer-torch official repository 6 samples, 6 ran (0 instrument-failed) · 0 unverified
count_parameters in 278 papers image_et/utils.py ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
gen_mask_id image_et/utils.py ran MIT (permissive) · 47b4e637f9d9e8f9 · report fixture: signature num_patch:int/0/int, mask_size:int/0/int, batch_size:int/0/int · returned tuple · level recorded 2026-09-25
get_files in 30 papers image_et/misc.py ran fingerprinted MIT (permissive) · 0c3b6f391746cf8b · report fixture: signature path:str/0/str, ext:str/0/str · returned list · level recorded 2026-09-25
get_latest_file in 5 papers image_et/misc.py ran fingerprinted MIT (permissive) · 3a6bd7dc66242ce6 · report fixture: signature path:str/0/str, ext:str/0/str · returned str · level recorded 2026-09-25
parse_number image_et/misc.py ran MIT (permissive) · a389ee3bf2f9a9dc · report fixture: signature name:str/0/str · returned int · level recorded 2026-09-25
unnormalize in 21 papers image_et/utils.py ran fingerprinted MIT (permissive) · d62e6f8bc4ddac46 · report fixture: signature x:Tensor/2/float, std:Tensor/1/float, mean:Tensor/1/float · returned Tensor · level recorded 2026-09-25
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
scaled_exp in 5 papers repository not located ran · our draft was wrong licence of this copy not recorded · 654acacaf00954fb · report fixture: signature field:str/0/str, scale_constant:float/0/float · returned function · level recorded 2026-09-22
src_dot_dst in 11 papers repository not located ran · our draft was wrong licence of this copy not recorded · 23fba400cff6fafa · report fixture: signature src_field:str/0/str, dst_field:str/0/str, out_field:str/0/str · returned function · level recorded 2026-09-22

Tasks

Anomaly DetectionGraph Anomaly DetectionGraph Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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