|
|
@@ -8,12 +8,12 @@ Highlighting top ML papers of the week.
|
|
|
|
|
|
| **Paper / Project** | **Link** |
|
|
|
| ------------- | ------------- |
|
|
|
-| 1. **Muse: Text-To-Image Generation via Masked Generative Transformers** -- 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](https://arxiv.org/abs/2301.00704) [Project](https://muse-model.github.io/)|
|
|
|
+| 1. **Muse: Text-To-Image Generation via Masked Generative Transformers** -- 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](https://arxiv.org/abs/2301.00704) , [Project](https://muse-model.github.io/)|
|
|
|
| 2. **VALL-E Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers** -- 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](https://valle-demo.github.io/) |
|
|
|
| 3. **Rethinking with Retrieval: Faithful Large Language Model Inference** -- 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](https://arxiv.org/abs/2301.00303) |
|
|
|
| 4. **SPARSEGPT: Massive Language Models Can Be Accurately Pruned In One-Shot** -- 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](https://arxiv.org/pdf/2301.00774.pdf) |
|
|
|
| 5. **ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders** -- ConvNeXt V2 is a performant model based on a fully convolutional masked autoencoder framework and other architectural improvements. CNNs are sticking back! | [Paper](https://arxiv.org/abs/2301.00808) |
|
|
|
-| 6. **Large Language Models as Corporate Lobbyists** -- 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](https://arxiv.org/abs/2301.01181) [Paper/Code/Data](https://github.com/JohnNay/llm-lobbyist) |
|
|
|
+| 6. **Large Language Models as Corporate Lobbyists** -- 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](https://arxiv.org/abs/2301.01181) , [Code](https://github.com/JohnNay/llm-lobbyist) |
|
|
|
| 7. **Superposition, Memorization, and Double Descent** -- 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](https://transformer-circuits.pub/2023/toy-double-descent/index.html) |
|
|
|
| 8. **StitchNet: Composing Neural Networks from Pre-Trained Fragments** -- 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](https://arxiv.org/abs/2301.01947) |
|
|
|
| 9. **Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes** -- Proposes integrated decomposition, an approach to improve Science Q&A through a human-in-the-loop workflow for refining compositional LM programs. | [Paper](https://arxiv.org/abs/2301.01751) |
|
angysaravia