new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK

Jul 31

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

·
32 authors

Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding

·
5 authors

Med-Flamingo: a Multimodal Medical Few-shot Learner

·
9 authors

PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization

·
5 authors

Robust Distortion-free Watermarks for Language Models

·
4 authors

Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields

·
7 authors

Exploring Format Consistency for Instruction Tuning

·
9 authors