Pith. sign in

REVIEW 4 cited by

Do Transformer Modifications Transfer Across Implementations and Applications?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.11972 v2 pith:RN3LZOA5 submitted 2021-02-23 cs.LG cs.CL

Do Transformer Modifications Transfer Across Implementations and Applications?

classification cs.LG cs.CL
keywords modificationstransformerexperimentalperformancerelativelyacrossadoptionapplications
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread adoption. In this paper, we comprehensively evaluate many of these modifications in a shared experimental setting that covers most of the common uses of the Transformer in natural language processing. Surprisingly, we find that most modifications do not meaningfully improve performance. Furthermore, most of the Transformer variants we found beneficial were either developed in the same codebase that we used or are relatively minor changes. We conjecture that performance improvements may strongly depend on implementation details and correspondingly make some recommendations for improving the generality of experimental results.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Ring Attention with Blockwise Transformers for Near-Infinite Context

    cs.CL 2023-10 unverdicted novelty 7.0

    Ring Attention uses blockwise computation and ring communication to let Transformers process sequences up to device-count times longer than prior memory-efficient methods.

  2. ST-MoE: Designing Stable and Transferable Sparse Expert Models

    cs.CL 2022-02 unverdicted novelty 6.0

    ST-MoE introduces stability techniques for sparse expert models, allowing a 269B-parameter model to achieve state-of-the-art transfer learning results across reasoning, summarization, and QA tasks at the compute cost ...

  3. When Does Removing LayerNorm Help? Activation Bounding as a Regime-Dependent Implicit Regularizer

    cs.LG 2026-04 unverdicted novelty 5.0

    DyT improves validation loss 27% at 64M params/1M tokens but worsens it 19% at 118M tokens, with saturation levels predicting the sign of the effect.

  4. CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models

    cs.CV 2025-08 unverdicted novelty 5.0

    CraftGraffiti applies LoRA-tuned diffusion transformers followed by identity-augmented self-attention and CLIP-guided pose extension to generate graffiti while preserving facial features.