Daily Overdose of Papers

14 posts

Daily Overdose of Papers banner
Daily Overdose of Papers

Daily Overdose of Papers

@DailyPapers

I want to talk to you about science. get paper overdosed, everyday

academia Katılım Ocak 2024
35 Takip Edilen10 Takipçiler
AK
AK@_akhaliq·
Meta presents Self-Rewarding Language Models paper page: huggingface.co/papers/2401.10… Fine-tuning Llama 2 70B on three iterations of our approach yields a model that outperforms many existing systems on the AlpacaEval 2.0 leaderboard, including Claude 2, Gemini Pro, and GPT-4 0613
AK tweet media
English
33
225
1.1K
464.6K
AK
AK@_akhaliq·
Google Deepmind announces AlphaGeometry An Olympiad-level AI system for geometry blog: deepmind.google/discover/blog/… AI system surpasses the state-of-the-art approach for geometry problems, advancing AI reasoning in mathematics
AK tweet media
English
4
81
449
48.7K
Google DeepMind
Google DeepMind@GoogleDeepMind·
Introducing AlphaGeometry: an AI system that solves Olympiad geometry problems at a level approaching a human gold-medalist. 📐 It was trained solely on synthetic data and marks a breakthrough for AI in mathematical reasoning. 🧵 dpmd.ai/alphageometry
GIF
English
119
948
3.9K
1.2M