SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.08332 · NeurIPS · 2024

UDON: Universal Dynamic Online distillatioN for generic image representations

Ondřej Chum, André Araujo, Kaifeng Chen, Nikolaos-Antonios Ypsilantis

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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, 1 violated it and 0 have no contract verdict; 3 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/2406.08332.json · badge: /api/ran/2406.08332.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
nikosips/UDON canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
create_one_example Ran
ran; our contract draft was wrong, not the code
nikosips/UDON/convert_to_tfrecord_from_file.py
pointer only (licence: NONE) · get_code("bd9d82ce47968423")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nikosips/UDON 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.

kl_divergence Ran
ran, violated the contract we drafted
nikosips/UDON/universal_embedding/loss_utils.py
pointer only (licence: NONE) · get_code("fbe85c54819c6bdf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nikosips/UDON 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.

load_split_info Ran
ran; our contract draft was wrong, not the code
nikosips/UDON/convert_to_tfrecord_from_file.py
pointer only (licence: NONE) · get_code("bb48115167af9337")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nikosips/UDON 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.

pick_output_shard Ran
ran, honoured the contract we drafted
nikosips/UDON/convert_to_tfrecord_from_file.py
pointer only (licence: NONE) · get_code("e402b1f2b5c4c027")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nikosips/UDON 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.

quick_gelu Ran
ran, honoured the contract we drafted
nikosips/UDON/universal_embedding/udon_clip_vit_with_embedding.py
pointer only (licence: NONE) · get_code("387ba0de72d89d99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nikosips/UDON 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.

udon_logits_distillation_loss Ran
ran; our contract draft was wrong, not the code
nikosips/UDON/universal_embedding/loss_utils.py
pointer only (licence: NONE) · get_code("79507a1f52ee5287")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nikosips/UDON 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Universal image representations are critical in enabling real-world fine-grained and instance-level recognition applications, where objects and entities from any domain must be identified at large scale. Despite recent advances, existing methods fail to capture important domain-specific knowledge, while also ignoring differences in data distribution across different domains. This leads to a large performance gap between efficient universal solutions and expensive approaches utilising a collection of specialist models, one for each domain. In this work, we make significant strides towards closing this gap, by introducing a new learning technique, dubbed UDON (Universal Dynamic Online distillatioN). UDON employs multi-teacher distillation, where each teacher is specialized in one domain, to transfer detailed domainspecific knowledge into the student universal embedding. UDON's distillation approach is not only effective, but also very efficient, by sharing most model parameters between the student and all teachers, where all models are jointly trained in an online manner. UDON also comprises a sampling technique which adapts the training process to dynamically allocate batches to domains which are learned slower and require more frequent processing. This boosts significantly the learning of complex domains which are characterised by a large number of classes and longtail distributions. With comprehensive experiments, we validate each component of UDON, and showcase significant improvements over the state of the art in the recent UnED benchmark. Code: https://github.com/nikosips/UDON.

For agents

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

get_harvested_code_for_paper("2406.08332")
get_code_for_paper("2406.08332")
have("2406.08332")

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

curl https://syntology.ai/api/ran/2406.08332.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.08332.svg)](https://syntology.ai/paper/2406.08332)

Connect an agent — have() is free.