Daily Papers of 2023-07-31

1. Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback 39 upvotes, #1 of 2023-07-31
2. Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding 39 upvotes, #1 of 2023-07-31
3. Med-Flamingo: a Multimodal Medical Few-shot Learner 25 upvotes, #3 of 2023-07-31
4. PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization 13 upvotes, #4 of 2023-07-31
5. Robust Distortion-free Watermarks for Language Models 9 upvotes, #5 of 2023-07-31
6. Exploring Format Consistency for Instruction Tuning 8 upvotes, #6 of 2023-07-31
7. Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields 6 upvotes, #7 of 2023-07-31

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.