SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.21035 · 2024

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 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/2410.21035.json · badge: /api/ran/2410.21035.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
jdeschena/sdtt canonical (classifier label)
classifier basis: census
10 ran · 0 no recorded run
FunctionStatusWhere it lives
bias_dropout_add_scale Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jdeschena/sdtt/src/sdtt/models/ar_orig.py
pointer only (licence: NONE); the stored copy get_code serves, from hxixixh/gumbel-distill, is pointer only (licence: NONE) · get_code("fbbc6722b74bda27")
How it ran

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

bias_dropout_add_scale_fused_train Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jdeschena/sdtt/src/sdtt/models/ar_orig.py
pointer only (licence: NONE); the stored copy get_code serves, from hxixixh/gumbel-distill, is pointer only (licence: NONE) · get_code("ee894c881614c3ec")
How it ran

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

eval_loop Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jdeschena/sdtt/src/sdtt/harness_gpt2.py
pointer only (licence: NONE) · get_code("b0a49b09dfb49452")
How it ran

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

get_bias_dropout_add_scale Ran
ran; our contract draft was wrong, not the code
jdeschena/sdtt/src/sdtt/models/ar_orig.py
pointer only (licence: NONE); the stored copy get_code serves, from jdeschena/blockgen, is pointer only (licence: NONE) · get_code("06d2d8e50f91481f")
How it ran

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

get_ckpt_idx Ran
ran, honoured the contract we drafted
jdeschena/sdtt/src/sdtt/push_to_hub.py
pointer only (licence: NONE) · get_code("a7222ce47d825dbf")
How it ran

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

gradient_norm Ran
ran, honoured the contract we drafted
jdeschena/sdtt/src/sdtt/callbacks/gradient_norm.py
pointer only (licence: NONE) · get_code("0f2e39e89855eac7")
How it ran

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

modulate Ran
ran, honoured the contract we drafted
jdeschena/sdtt/src/sdtt/models/dit_orig.py
pointer only (licence: NONE); the stored copy get_code serves, from hxixixh/gumbel-distill, is pointer only (licence: NONE) · get_code("78b555034273f3c7")
How it ran

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

parse_str_int_list Ran
ran, honoured the contract we drafted
jdeschena/sdtt/src/sdtt/utils.py
pointer only (licence: NONE) · get_code("e23c2025aad80db2")
How it ran

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

rm_null_values Ran
ran; our contract draft was wrong, not the code
jdeschena/sdtt/src/sdtt/utils.py
pointer only (licence: NONE) · get_code("8c79294eaaaef612")
How it ran

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

str_to_dtype Ran
ran; our contract draft was wrong, not the code
jdeschena/sdtt/src/sdtt/utils.py
pointer only (licence: NONE) · get_code("9811c7dc90993af3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jdeschena/sdtt 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
modulate 9 other papers
9 later · 1 only as an assembly brick
2412.10193 (2024-12)
Simple Guidance Mechanisms for Discrete Diffusion Models
2503.09573 (2025-03)
BLOCK DIFFUSION: INTERPOLATING BETWEEN AU-TOREGRESSIVE AND DIFFUSION LANGUAGE MODELS
2505.18883 (2025-05)
Partition Generative Modeling: Masked Modeling Without Masks
and 6 more not named here
get_bias_dropout_add_scale 8 other papers
2 dated earlier, 6 later
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2405.20971 (2024-05)
Amortizing intractable inference in diffusion models for vision, language, and control
2412.10193 (2024-12)
Simple Guidance Mechanisms for Discrete Diffusion Models
and 5 more not named here
bias_dropout_add_scale 7 other papers
7 later
2503.09573 (2025-03)
BLOCK DIFFUSION: INTERPOLATING BETWEEN AU-TOREGRESSIVE AND DIFFUSION LANGUAGE MODELS
2505.18883 (2025-05)
Partition Generative Modeling: Masked Modeling Without Masks
2509.15188 (2025-09)
Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
and 4 more not named here
bias_dropout_add_scale_fused_train 5 other papers
5 later
2503.09573 (2025-03)
BLOCK DIFFUSION: INTERPOLATING BETWEEN AU-TOREGRESSIVE AND DIFFUSION LANGUAGE MODELS
2505.18883 (2025-05)
Partition Generative Modeling: Masked Modeling Without Masks
2509.15188 (2025-09)
Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
and 2 more not named here
eval_loop 1 other paper
1 the same month
2410.08709 (2024-10)
Distillation of Discrete Diffusion through Dimensional Correlations

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

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to generate one token at a time, which can result in noticeable latency. Recent advances have indicated that search and repeated sampling can enhance performance in various applications, such as theorem proving, code generation, and alignment, by utilizing greater computational resources during inference. In this study, we demonstrate that diffusion language models are capable of generating at least 32 tokens simultaneously, while exceeding the performance of AR models in text quality and on the LAMBADA natural language understanding benchmark. This outcome is achieved through a novel distillation method for discrete diffusion models, which reduces the number of inference steps by a factor of 32-64. Practically, at the 1.3B parameters scale, diffusion models, even without caching, can generate tokens at a rate that is up to 8 times faster than AR models employing KV-caching, and we anticipate further improvements with the inclusion of caching. Moreover, we demonstrate the efficacy of our approach for diffusion language models with up to 860M parameters.

For agents

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

get_harvested_code_for_paper("2410.21035")
get_code_for_paper("2410.21035")
have("2410.21035")

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

curl https://syntology.ai/api/ran/2410.21035.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.21035.svg)](https://syntology.ai/paper/2410.21035)

Connect an agent — have() is free.