SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.04577 · EMNLP · 2025

Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers

Chao Xu, Lei Shang, Shujun Wang, Zhe Hu, Haoyu Xie, Juncheng Wang, Cheng Yu, Guoqi Yu, Tokenizer De-Tokenizer, Reconstructions

arXiv · PDF · Open in the Atlas

Code that ran

7 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 6 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/2510.04577.json · badge: /api/ran/2510.04577.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
wjc2830/Siren community
Papers with Code archive
7 ran · 6 no recorded run
FunctionStatusWhere it lives
DacCodebookLayer Ran
ran on a synthesized input · constructed an object; no result was computed
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("b6cc0d213723cc49")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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.

DacEmbeddingState Ran
ran on a synthesized input · constructed an object; no result was computed
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("34e282922212d09b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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.

RMSNorm Ran
ran on a synthesized input · constructed an object; no result was computed
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("9669b074ff77501a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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.

SirenConfig Ran
ran on a synthesized input · constructed an object; no result was computed
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("2259770fbb6b2e31")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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.

SwiGLU Ran
ran on a synthesized input · constructed an object; no result was computed
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("a71ae52495d11b8d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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.

_round_up Ran
ran, honoured the contract we drafted
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("7730a366fecd0601")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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.

sinusoidal_positions Ran
ran, honoured the contract we drafted
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("862fce0d4bd982cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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.

CausalSelfAttention Not yet run
unverified (harvested, no recorded run)
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("0f22591f0eeeaeb3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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. No invocation recorded.

CrossAttention Not yet run
unverified (harvested, no recorded run)
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("cda35aded4b4d4c8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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. No invocation recorded.

CrossTransformerBlock Not yet run
unverified (harvested, no recorded run)
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("b532c32a7f5f8e09")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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. No invocation recorded.

DacCodebookBank Not yet run
unverified (harvested, no recorded run)
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("b2adb2176bc76364")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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. No invocation recorded.

SirenExpert Not yet run
unverified (harvested, no recorded run)
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("0f92e3904bec5c96")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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. No invocation recorded.

TransformerBlock Not yet run
unverified (harvested, no recorded run)
wjc2830/Siren/src/siren/model.py
pointer only (licence: NONE) · get_code("569eaf68130b8046")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wjc2830/Siren 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. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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

While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma underpinning this gap: incorporating more RVQ layers improves audio reconstruction fidelity but exceeds the generation capacity of conventional LMs. To address this, we first analyze RVQ dynamics and uncover two key limitations: 1) orthogonality of features across RVQ layers hinders effective LMs training, and 2) descending semantic richness in tokens from deeper RVQ layers exacerbates exposure bias during autoregressive decoding. Based on these insights, we propose Siren, a novel LM-based framework that employs multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning. Extensive experiments demonstrate that Siren outperforms both existing LM-based and diffusion-based T2A systems, achieving state-of-the-art results. By bridging the representational strengths of LMs with the fidelity demands of audio synthesis, our approach repositions LMs as competitive contenders against diffusion models in T2A tasks. Moreover, by aligning audio representations with linguistic structures, Siren facilitates a promising pathway toward unified multimodal generation frameworks. The code is released at https://github.com/wjc2830/Siren.git.

For agents

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

get_harvested_code_for_paper("2510.04577")
get_code_for_paper("2510.04577")
have("2510.04577")

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

curl https://syntology.ai/api/ran/2510.04577.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.04577.svg)](https://syntology.ai/paper/2510.04577)

Connect an agent — have() is free.