Daily Papers of 2023-06-13

1. FasterViT: Fast Vision Transformers with Hierarchical Attention 32 upvotes, #1 of 2023-06-13
2. Controlling Text-to-Image Diffusion by Orthogonal Finetuning 25 upvotes, #2 of 2023-06-13
3. Benchmarking Neural Network Training Algorithms 22 upvotes, #3 of 2023-06-13
4. Augmenting Language Models with Long-Term Memory 19 upvotes, #4 of 2023-06-13
5. Face0: Instantaneously Conditioning a Text-to-Image Model on a Face 18 upvotes, #5 of 2023-06-13
6. Scalable 3D Captioning with Pretrained Models 17 upvotes, #6 of 2023-06-13
7. High-Fidelity Audio Compression with Improved RVQGAN 13 upvotes, #7 of 2023-06-13
8. Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence 11 upvotes, #8 of 2023-06-13
9. Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptions 10 upvotes, #9 of 2023-06-13
10. Transformers learn through gradual rank increase 10 upvotes, #9 of 2023-06-13
11. Retrieval-Enhanced Contrastive Vision-Text Models 8 upvotes, #11 of 2023-06-13
12. Weakly supervised information extraction from inscrutable handwritten document images 4 upvotes, #12 of 2023-06-13

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.