In this issue, we cover the top ML Papers of the Week (Feb 6 - Feb 12).
1). Toolformer - introduces language models that teach themselves to use external tools via simple API calls. (paper)
![Twitter avatar for @timo_schick](https://substackcdn.com/image/twitter_name/w_96/timo_schick.jpg)
![Image](https://substackcdn.com/video/upload/e_loop,vs_40/zjlrftmolghuqamwmj8p.gif)
2). Describe, Explain, Plan, and Select - proposes using language models for open-world game playing. (paper)
![Twitter avatar for @jeasinema](https://substackcdn.com/image/twitter_name/w_96/jeasinema.jpg)
![Image](https://substackcdn.com/image/fetch/w_600,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fpbs.substack.com%2Fmedia%2FFoP-9AQaYAAx8eh.jpg)
3). A Categorical Archive of ChatGPT Failures - a comprehensive analysis of ChatGPT failures for categories like reasoning, factual errors, maths, and coding. (paper)
![Twitter avatar for @omarsar0](https://substackcdn.com/image/twitter_name/w_96/omarsar0.jpg)
![Image](https://substackcdn.com/image/fetch/w_600,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fpbs.substack.com%2Fmedia%2FFoaPNZcXgAEaXU4.png)
4). Hard Prompts Made Easy - optimizing hard text prompts through efficient gradient-based optimization. (paper)
![Twitter avatar for @tomgoldsteincs](https://substackcdn.com/image/twitter_name/w_96/tomgoldsteincs.jpg)
![Image](https://substackcdn.com/image/fetch/w_600,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fpbs.substack.com%2Fmedia%2FFodToukXEAABpdf.jpg)
5). Data Selection for LMs - proposes a cheap and scalable data selection framework based on an importance resampling algorithm to improve the downstream performance of LMs. (paper)
![Twitter avatar for @sangmichaelxie](https://substackcdn.com/image/twitter_name/w_96/sangmichaelxie.jpg)
![Image](https://substackcdn.com/image/fetch/w_600,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fpbs.substack.com%2Fmedia%2FFoaWcFZacAAlttT.jpg)
6). Gen-1 - proposes an approach for structure and content-guided video synthesis with diffusion models. (paper)
![Twitter avatar for @AlphaSignalAI](https://substackcdn.com/image/twitter_name/w_96/AlphaSignalAI.jpg)
7). Multitask, Multilingual, Multimodal Evaluation of ChatGPT - performs a more rigorous evaluation of ChatGPt on reasoning, hallucination, and interactivity. (paper)
![Twitter avatar for @omarsar0](https://substackcdn.com/image/twitter_name/w_96/omarsar0.jpg)
![Image](https://substackcdn.com/image/fetch/w_600,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fpbs.substack.com%2Fmedia%2FFofYnNXWAAEEQlc.png)
![Image](https://substackcdn.com/image/fetch/w_600,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fpbs.substack.com%2Fmedia%2FFofYqaPWIAA6IWL.png)
![Image](https://substackcdn.com/image/fetch/w_600,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fpbs.substack.com%2Fmedia%2FFofY1sPXwAIld-9.png)
8). Noise2Music - proposes diffusion models to generate high-quality 30-second music clips via text prompts. (paper)
![Twitter avatar for @_akhaliq](https://substackcdn.com/image/twitter_name/w_96/_akhaliq.jpg)
9). Offsite-Tuning - introduces an efficient, privacy-preserving transfer learning framework to adapt foundational models to downstream data without access to the full model. (paper)
![Twitter avatar for @arankomatsuzaki](https://substackcdn.com/image/twitter_name/w_96/arankomatsuzaki.jpg)
![Image](https://substackcdn.com/image/fetch/w_600,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fpbs.substack.com%2Fmedia%2FFor2vX7WIAABkqE.png)
10). pix2pix-zero - proposes a model for zero-shot image-to-image translation. (paper)
![Twitter avatar for @arankomatsuzaki](https://substackcdn.com/image/twitter_name/w_96/arankomatsuzaki.jpg)
See you next week for another round of awesome ML papers!