Papers › Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

24 May 2025arXiv:2505.18600archive 2025-07-28

Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye

Modern single-image super-resolution (SISR) models deliver photo-realistic results at the scale factors on which they are trained, but collapse when asked to magnify far beyond that regime. We address this scalability bottleneck with Chain-of-Zoom (CoZ), a model-agnostic framework that factorizes SISR into an autoregressive chain of intermediate scale-states with multi-scale-aware prompts. CoZ repeatedly re-uses a backbone SR model, decomposing the conditional probability into tractable sub-problems to achieve extreme resolutions without additional training. Because visual cues diminish at high magnifications, we augment each zoom step with multi-scale-aware text prompts generated by a vision-language model (VLM). The prompt extractor itself is fine-tuned using Generalized Reward Policy Optimization (GRPO) with a critic VLM, aligning text guidance towards human preference. Experiments show that a standard 4x diffusion SR model wrapped in CoZ attains beyond 256x enlargement with high perceptual quality and fidelity. Project Page: https://bryanswkim.github.io/chain-of-zoom/ .

PaperPDFCode Syntology ranMethod as code

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 20 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 5 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: found in paper text by Syntology: 20 samples from 1 repository, 12 ran (5 with no instrument failure; 7 where Syntology's instrument failed). 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

cswry/OSEDiff found in paper text by SyntologyApache-2.0Syntology: 20 samples, 12 ran (7 instrument-failed) · 8 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

20 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 8 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.

5ran · our draft was wrong
2ran; the contract check could not run
5ran
8unverified

Licence: 0 of the 20 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 cswry/OSEDiff. “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.

cswry/OSEDiff found in paper text by Syntology 20 samples, 12 ran (7 instrument-failed) · 8 unverified
GroupNormParam my_utils/vaehook.py ran Apache-2.0 (permissive) · cd284aab598a07c2 · report fixture: signature tile:Tensor/5/float, layer:callable/0/? · returned NoneType · level recorded 2026-09-24
attn_forward in 6 papers my_utils/vaehook.py ran · our draft was wrong Apache-2.0 (permissive) · bc23635609cf5e46 · report fixture: signature self:callable/0/?, h_:Tensor/4/float · returned Tensor · level recorded 2026-09-22
attn_forward_new in 5 papers my_utils/vaehook.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · ad8c4ea29723e250 · report fixture: signature self:callable/0/?, h_:Tensor/4/float · returned Tensor · level recorded 2026-09-22
clone_task_queue my_utils/vaehook.py ran · our draft was wrong Apache-2.0 (permissive) · 05623218f00496b1 · report fixture: signature task_queue:list/1/list · returned list · level recorded 2026-09-22
crop_valid_region my_utils/vaehook.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 4f5087c964be075a · report fixture: signature x:Tensor/4/float, input_bbox:list/1/int, target_bbox:list/1/int, is_decoder:bool/0/bool · returned Tensor · level recorded 2026-09-22
custom_group_norm my_utils/vaehook.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b9bb34c9f6fa3f19 · report fixture: signature input:Tensor/4/float, num_groups:int/0/int, mean:Tensor/1/float, var:Tensor/1/float, weight:Tensor/1/float, bias:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
get_cuda_device_string my_utils/vaehook.py ran Apache-2.0 (permissive) · 5b18dd6258dda3ac · report fixture: returned str · level recorded 2026-09-22
get_optimal_device my_utils/vaehook.py ran Apache-2.0 (permissive) · c0cb908a86960b3e · report fixture: returned device · level recorded 2026-09-22
get_optimal_device_name my_utils/vaehook.py ran Apache-2.0 (permissive) · fdb5f42c95e7ce7c · report fixture: returned str · level recorded 2026-09-22
get_var_mean my_utils/vaehook.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2c31ab46d2d7816d · report fixture: signature input:Tensor/4/float, num_groups:int/0/int, eps:float/0/float · returned tuple · level recorded 2026-09-22
has_mps my_utils/vaehook.py ran Apache-2.0 (permissive) · d5f22536dca7a551 · report fixture: returned bool · level recorded 2026-09-22
inplace_nonlinearity in 5 papers my_utils/vaehook.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 76a017e88938061d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
NansException my_utils/vaehook.py unverified Apache-2.0 (permissive) · 12b0a428903ea66d · report
VAEHook my_utils/vaehook.py unverified Apache-2.0 (permissive) · a24a63fdf5977e44 · report
attn2task my_utils/vaehook.py unverified Apache-2.0 (permissive) · 8bae659fb7d40d76 · report
build_sampling my_utils/vaehook.py unverified Apache-2.0 (permissive) · 7a660644b945f53b · report
build_task_queue my_utils/vaehook.py unverified Apache-2.0 (permissive) · 28e56cf67d286e05 · report
resblock2task my_utils/vaehook.py unverified Apache-2.0 (permissive) · 6d2cccfb582558a7 · report
test_for_nans my_utils/vaehook.py unverified Apache-2.0 (permissive) · 3164631c0de24c4f · report
xformer_attn_forward my_utils/vaehook.py unverified Apache-2.0 (permissive) · a97f72f307904874 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Chain-of-Zoom (graph method: Chain-of-Zoom). 20 bricks; individually on a fixture: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. VAEHook entry · level 0 · unverified · a24a63fdf5977e44
  2. GroupNormParam helper · level 1 · ran · cd284aab598a07c2
  3. build_task_queue model · level 0 · unverified · 28e56cf67d286e05
  4. clone_task_queue helper · level 1 · ran · our draft was wrong · 05623218f00496b1
  5. crop_valid_region helper · level 1 · ran; the contract check could not run (RAISES) · 4f5087c964be075a
  6. get_optimal_device helper · level 1 · ran · c0cb908a86960b3e
  7. test_for_nans helper · level 0 · unverified · 3164631c0de24c4f
  8. custom_group_norm model · level 1 · ran · our draft was wrong · b9bb34c9f6fa3f19
  9. get_var_mean helper · level 1 · ran · our draft was wrong · 2c31ab46d2d7816d
  10. build_sampling model · level 0 · unverified · 7a660644b945f53b
  11. inplace_nonlinearity helper · level 1 · ran · our draft was wrong · 76a017e88938061d
  12. get_optimal_device_name helper · level 1 · ran · fdb5f42c95e7ce7c
  13. NansException helper · level 0 · unverified · 12b0a428903ea66d
  14. attn2task helper · level 0 · unverified · 8bae659fb7d40d76
  15. resblock2task helper · level 0 · unverified · 6d2cccfb582558a7
  16. get_cuda_device_string helper · level 1 · ran · 5b18dd6258dda3ac
  17. has_mps helper · level 1 · ran · d5f22536dca7a551
  18. attn_forward model · level 1 · ran · our draft was wrong · bc23635609cf5e46
  19. attn_forward_new helper · level 1 · ran; the contract check could not run (RAISES) · ad8c4ea29723e250
  20. xformer_attn_forward model · level 0 · unverified · a97f72f307904874

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2505.18600") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Super-ResolutionLanguage ModelingLanguage ModellingSuper-Resolution

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