Submitted by akhaliq 100 ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs · 18 authors 5
Submitted by akhaliq 37 Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding · 5 authors 2
Submitted by akhaliq 37 Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback · 32 authors 4
Submitted by akhaliq 12 PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization · 5 authors
Submitted by akhaliq 6 Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields · 7 authors