SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.07615 · ICML · 2026

Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models

José Hernández-Lobato, Bin Li, Xiao Li, Jiahao Li, Yan Lu, Zongyu Guo, Jiajun He, Zhaoyang Jia, Xiaoyi Zhang

arXiv · PDF · Open in the Atlas

Code that ran

None of the 5 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (5 no recorded run), measured 2026-11-22; 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/2603.07615.json · badge: /api/ran/2603.07615.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
hmkx/NVRC canonical (classifier label)
classifier basis: census
0 ran · 5 no recorded run
FunctionStatusWhere it lives
broadcast_prior Not yet run
unverified (harvested, no recorded run)
hmkx/NVRC/entropy_models/utils.py
code served (permissive licence) · get_code("b6bcfafaafc98d13")
How it ran

no invocation recorded.

log_mse Not yet run
unverified (harvested, no recorded run)
hmkx/NVRC/losses.py
code served (permissive licence) · get_code("2defccb297217e17")
How it ran

no invocation recorded.

mse Not yet run
unverified (harvested, no recorded run)
hmkx/NVRC/losses.py
code served (permissive licence) · get_code("1a1a61c85538d493")
How it ran

no invocation recorded.

params_to_vector Not yet run
unverified (harvested, no recorded run)
hmkx/NVRC/entropy_models/utils.py
code served (permissive licence) · get_code("aac3c190757d55ee")
How it ran

no invocation recorded.

yuv444to420 Not yet run
unverified (harvested, no recorded run)
hmkx/NVRC/losses.py
code served (permissive licence) · get_code("49bb335597faa669")
How it ran

no invocation 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

Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external to the model and cannot directly exploit this knowledge for compact storage or reuse. In this work, we introduce a new visual representation framework that encodes a signal as a function, which is parametrized by low-rank adaptations attached to a frozen visual generative model. Such implicit representations of visual signals, e.g., an 81-frame video, can further be hashed into a single compact vector, achieving strong perceptual video compression at extremely low bitrates. Beyond basic compression, the functional nature of this representation enables inference-time scaling and control, allowing additional refinement on the compression performance. More broadly, as the implicit representations directly act as a function of the generation process, this suggests a unified framework bridging visual compression and generation.

For agents

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

get_harvested_code_for_paper("2603.07615")
get_code_for_paper("2603.07615")
have("2603.07615")

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

curl https://syntology.ai/api/ran/2603.07615.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.07615.svg)](https://syntology.ai/paper/2603.07615)

Connect an agent — have() is free.