SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.17124 · 2026

iFSQ: Improving FSQ for Image Generation with 1 Line of Code

Zhao Zhong, Li Yuan, Kaixiong Gong, Jianwei Zhang, Bin Lin, Liefeng Bo, Yuwei Niu, Mingzhe Zheng, Yunlong Lin, Miles Yang, Zongjian Li, Yunyang Ge

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 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/2601.17124.json · badge: /api/ran/2601.17124.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
Tencent-Hunyuan/iFSQ community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
GroupFSQ Ran
ran on a synthesized input · constructed an object; no result was computed
Tencent-Hunyuan/iFSQ/ifsq/src/model/modules/fsq.py
pointer only (licence: NOASSERTION) · get_code("c423337b9d614960")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Tencent-Hunyuan/iFSQ (NOASSERTION). 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.

round_ste Ran
ran; our contract draft was wrong, not the code
Tencent-Hunyuan/iFSQ/ifsq/src/model/modules/fsq.py
pointer only (licence: NOASSERTION) · get_code("47dd83e6ed9c70bc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Tencent-Hunyuan/iFSQ (NOASSERTION). 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.

default Not yet run
unverified (harvested, no recorded run)
Tencent-Hunyuan/iFSQ/ifsq/src/model/modules/fsq.py
pointer only (licence: NOASSERTION) · get_code("1b2b2b42c9263ba4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Tencent-Hunyuan/iFSQ (NOASSERTION). 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. No invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

FunctionAlso present inEarliest-datedOthers named
round_ste
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2411.19842 (2024-11)
Scaling Transformers for Low-Bitrate High-Quality Speech Coding

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

The field of image generation is currently bifurcated into autoregressive (AR) models operating on discrete tokens and diffusion models utilizing continuous latents. This divide, rooted in the distinction between VQ-VAEs and VAEs, hinders unified modeling and fair benchmarking. Finite Scalar Quantization (FSQ) offers a theoretical bridge, yet vanilla FSQ suffers from a critical flaw: its equal-interval quantization can cause activation collapse. This mismatch forces a trade-off between reconstruction fidelity and information efficiency. In this work, we resolve this dilemma by simply replacing the activation function in original FSQ with a distribution-matching mapping to enforce a uniform prior. Termed iFSQ, this simple strategy requires just one line of code yet mathematically guarantees both optimal bin utilization and reconstruction precision. Leveraging iFSQ as a controlled benchmark, we uncover two key insights: (1) The optimal equilibrium between discrete and continuous representations lies at approximately 4 bits per dimension. (2) Under identical reconstruction constraints, AR models exhibit rapid initial convergence, whereas diffusion models achieve a superior performance ceiling, suggesting that strict sequential ordering may limit the upper bounds of generation quality. Finally, we extend our analysis by adapting Representation Alignment (REPA) to AR models, yielding LlamaGen-REPA. Codes is available at https://github.com/Tencent-Hunyuan/iFSQ.

For agents

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

get_harvested_code_for_paper("2601.17124")
get_code_for_paper("2601.17124")
have("2601.17124")

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

curl https://syntology.ai/api/ran/2601.17124.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.17124.svg)](https://syntology.ai/paper/2601.17124)

Connect an agent — have() is free.