| 1. GoogleAI introduces Muse, a new text-to-image generation model based on masked generative transformers; significantly more efficient than other diffusion models like Imagen and DALLE-2. |
Paper Project |
| 2. Microsoft introduces VALL-E, a text-to-audio model that performs state-of-the-art zero-shot performance; the text-to-speech synthesis task is treated as a conditional language modeling task: |
Project |
| 3. A new paper shows the potential of enhancing LLMs by retrieving relevant external knowledge based on decomposed reasoning steps obtained through chain-of-thought prompting. |
Paper |
| 4. Presents a technique for compressing large language models while not sacrificing performance; "pruned to at least 50% sparsity in one-shot, without any retraining." |
Paper |
| 5. ConvNeXt V2 is a performant model based on a fully convolutional masked autoencoder framework and other architectural improvements. CNNs are sticking back! |
Paper |
| 6. With more capabilities, we are starting to see a wider range of applications with LLMs. This paper utilized large language models for conducting corporate lobbying activities. |
Paper |
| 7. This work aims to better understand how deep learning models overfit or memorize examples; interesting phenomena observed; important work toward a mechanistic theory of memorization. |
Paper |
| 8. StitchNet: Interesting idea to create new coherent neural networks by reusing pretrained fragments of existing NNs. Not straightforward but there is potential in terms of efficiently reusing learned knowledge in pre-trained networks for complex tasks. |
Paper |
| 9. Proposes integrated decomposition, an approach to improve Science Q&A through a human-in-the-loop workflow for refining compositional LM programs. |
Paper |
| 10. A Succinct Summary of Reinforcement Learning. A nice little overview of some important ideas in RL. |
Paper |
angysaravia
cdedbf182b
Update README.md