Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A curated list of awesome resources combining Transformers with Neural Architecture Search
| Date | Stars |
|---|---|
| 2026-07-24 | 270 |
| 2026-07-25 | 270 |
| 2026-07-28 | 270 |
| 2026-07-30 | 270 |
| 2026-08-06 | 270 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Transformer Architecture Search: [](https://awesome.re) <p align="center"> <img width="250" src="https://camo.githubusercontent.com/1131548cf666e1150ebd2a52f44776d539f06324/68747470733a2f2f63646e2e7261776769742e636f6d2f73696e647265736f726875732f617765736f6d652f6d61737465722f6d656469612f6c6f676f2e737667" "Awesome!"> </p> To keep track of the large number of recent papers that look at the intersection of Transformers and Neural Architecture Search (NAS), we have created this _awesome_ list of curated papers and resources, inspired by [awesome-autodl](https://github.com/D-X-Y/Awesome-AutoDL), [awesome-architecture-search](https://github.com/markdtw/awesome-architecture-search), and [awesome-computer-vision](https://github.com/jbhuang0604/awesome-computer-vision). Papers are divided into the following categories: 1. [**General Transformer search**](#general-transformer-search) 2. [**Domain Specific, applied Transformer search (divided into NLP, Vision, ASR)**](#domain-specific-transformer-search) 3. [**Transformers Knowledge: Insights / Searchable parameters / Attention**](#transformers-knowledge-insights-searchable-parameters-attention) 4. [**Transformer Surveys**](#transformer-surveys) 5. [**Foundation Models**](#foundation-models) 6. [**Misc Resources**](#misc-resources) This repository is maintained by [**Yash Mehta**](https://yashsmehta.github.io/), please feel free to reach out, create [pull requests](https://github.com/automl/awesome-transformer-search/pulls) or [open an issue](https://github.com/automl/awesome-transformer-search/issues) to add papers. Please see this [**Google Doc**](https://shorturl.at/giuFG) for a comprehensive list of papers at **ICML 2023** on foundation models/large language models. ## General Transformer Search | Title | Venue | Group | |:--------------------------------------------------------------------------------------------------------|:--------------|:-----------------------| | [Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models](https://openreview.net/forum?id=GdMqXQx5fFR) | **NeurIPS'22** | MSR | | [Training Free Transformer Architecture Search](https://arxiv.org/abs/2203.12217) | **CVPR'22** | Tencent & Xiamen University | | [LiteTransformerSearch: Training-free On-device Search for Efficient Autoregressive Language Models](https://arxiv.org/pdf/2203.02094.pdf) | AutoML Conference 2022 Workshop Track | MSR | | [Searching the Search Space of Vision Transformer](https://proceedings.neurips.cc/paper/2021/file/48e95c45c8217961bf6cd7696d80d238-Paper.pdf) | **NeurIPS'21** | MSRA, Stony Brook University | | [UniNet: Unified Architecture Search with Convolutions, Transformer and MLP](https://arxiv.org/pdf/2110.04035.pdf) | ECCV'22 | SenseTime | | [Analyzing and Mitigating Interference in Neural Architecture Search](https://proceedings.mlr.press/v162/xu22h.html) | **ICML'22** | Tsinghua, MSR | | [BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search](https://arxiv.org/pdf/2103.12424.pdf) | **ICCV'21** | Sun Yat-sen University | | [Memory-Efficient Differentiable Transformer Architecture Search](https://aclanthology.org/2021.findings-acl.372.pdf) | **ACL-IJCNLP'21** | MSR, Peking University | | [Finding Fast Transformers: One-Shot Neural Architecture Search by Component Composition](https://arxiv.org/pdf/2008.06808.pdf) | arxiv [Aug'20] | Google Research | | [AutoTrans: Automating Transformer Design via Reinforced Architecture Search](https://arxiv.org/pdf/2009.02070.pdf) | NLPCC'21 | Fudan Un
Excerpt of 16,064 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4f6a8c7ec9709f42, topic:transformer, readme:transformer architecture