SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.06130 · NAACL · 2022

Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation

Jinyi Hu, Maosong Sun, Wenhao Li, Xing Xie, Xiaoyuan Yi

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2207.06130.json · badge: /api/ran/2207.06130.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
OpenVLG/DELLA canonical (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_au Ran
ran, honoured the contract we drafted
OpenVLG/DELLA/train_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from trustedllm/regavae, is pointer only (licence: NONE) · get_code("2887245599da5a9d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from trustedllm/regavae, and GitHub detected no licence in that repository 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.

calc_iwnll Ran
ran, honoured the contract we drafted
OpenVLG/DELLA/train_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from trustedllm/regavae, is pointer only (licence: NONE) · get_code("046dedc52d7678ab")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from trustedllm/regavae, and GitHub detected no licence in that repository 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.

log_sum_exp Ran
ran; our contract draft was wrong, not the code
OpenVLG/DELLA/train_utils.py
code served (permissive licence) · get_code("5efe6eb2209f6591")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor for testing log_sum_exp
# The function operates on a single tensor and optionally reduces along a dimension
value = torch.randn(2, 4)

# Test case 1: with dim specified
ARGS = {
    "value": value,
    "dim": 1,
    "keepdim": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
soft_clamp5 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
OpenVLG/DELLA/dist.py
pointer only (licence: MIT); the stored copy get_code serves, from trustedllm/regavae, is pointer only (licence: NONE) · get_code("cd334034d398bfaa")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from trustedllm/regavae, and GitHub detected no licence in that repository 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 0 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
log_sum_exp 5 other papers
3 dated earlier, 2 later
1901.05534 (2019-01)
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
2004.12585 (2020-04)
A Batch Normalized Inference Network Keeps the KL Vanishing Away
2110.12381 (2021-10)
Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness
and 2 more not named here
soft_clamp5 3 other papers
1 dated earlier, 2 later
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
2023.findings-emnlp.313 (2023 (year only))
Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation
2310.10567 (2023-10)
RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling
calc_au 1 other paper
1 later
2310.10567 (2023-10)
RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling
calc_iwnll 1 other paper
1 later
2310.10567 (2023-10)
RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling

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 past several years have witnessed Variational Auto-Encoder's superiority in various text generation tasks. However, due to the sequential nature of the text, auto-regressive decoders tend to ignore latent variables and then reduce to simple language models, known as the KL vanishing problem, which would further deteriorate when VAE is combined with Transformer-based structures. To ameliorate this problem, we propose DELLA, a novel variational Transformer framework. DELLA learns a series of layer-wise latent variables with each inferred from those of lower layers and tightly coupled with the hidden states by low-rank tensor product. In this way, DELLA forces these posterior latent variables to be fused deeply with the whole computation path and hence incorporate more information. We theoretically demonstrate that our method can be regarded as entangling latent variables to avoid posterior information decrease through layers, enabling DELLA to get higher nonzero KL values even without any annealing or thresholding tricks. Experiments on four unconditional and three conditional generation tasks show that DELLA could better alleviate KL vanishing and improve both quality and diversity compared to several strong baselines.

For agents

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

get_harvested_code_for_paper("2207.06130")
get_code_for_paper("2207.06130")
have("2207.06130")

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

curl https://syntology.ai/api/ran/2207.06130.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.06130.svg)](https://syntology.ai/paper/2207.06130)

Connect an agent — have() is free.