Daily Papers of 2023-09-18

1. Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers 53 upvotes, #1 of 2023-09-18
2. Replacing softmax with ReLU in Vision Transformers 18 upvotes, #2 of 2023-09-18
3. Scaling Laws for Sparsely-Connected Foundation Models 15 upvotes, #3 of 2023-09-18
4. Sparse Autoencoders Find Highly Interpretable Features in Language Models 15 upvotes, #3 of 2023-09-18
5. Investigating Answerability of LLMs for Long-Form Question Answering 14 upvotes, #5 of 2023-09-18
6. LASER: LLM Agent with State-Space Exploration for Web Navigation 13 upvotes, #6 of 2023-09-18
7. Compositional Foundation Models for Hierarchical Planning 10 upvotes, #7 of 2023-09-18
8. Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping 8 upvotes, #8 of 2023-09-18
9. Leveraging Contextual Information for Effective Entity Salience Detection 7 upvotes, #9 of 2023-09-18
10. A Data Source for Reasoning Embodied Agents 6 upvotes, #10 of 2023-09-18
11. Retrieval-Augmented Text-to-Audio Generation 6 upvotes, #10 of 2023-09-18
12. Viewpoint Textual Inversion: Unleashing Novel View Synthesis with Pretrained 2D Diffusion Models 3 upvotes, #12 of 2023-09-18

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.