This survey reviews techniques for enhancing LLM inference through computation, exploring independent, context-aware, and model-aided self-improvement, while discussing challenges and future research directions.

https://arxiv.org/abs//2412.14352

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers