追踪最新科研动态，5月热门必读论文

哈喽大家好，5月热门论文必读论文总结来啦！

在过去的5月，谷歌和OpenAI双双提出“技术报告”，谷歌提出PaLM-2，推理超越 GPT-4，而OpenAI直指DeepMind，出手解决GPT-4数学推理，论文数据集全开放。

大模型从去年ChatGPT发布后到今年5月，一直是热门研究方向。根据AMiner平台论文浏览量和收藏量，5月，一共有35篇热门论文新鲜出炉，分别来自OpenAI、谷歌、Meta、微软、清华大学、华为等机构。

论文列表如下（点击阅读原文可直接使用ChatPaper）：

1.QLORA: Efficient Finetuning of Quantized LLMs

2.Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

3.Let’s Verify Step by Step

4.OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities

5.Voyager: An Open-Ended Embodied Agent with Large Language Models

6.Tree of Thoughts: Deliberate Problem Solving with Large Language Models

7.Backpack Language Models

8.Controllable Text-to-Image Generation with GPT-4

9.HuatuoGPT, towards Taming Language Model to Be a Doctor

10.Large Language Models as Tool Makers

11.Specifer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification

12.Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

13.ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

14.RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

15.Ghost in the Minecraft: Generally Capable Agents for Open-World Enviroments via Large Language Models with Text-based Knowledge and Memory

16.VanillaNet: the Power of Minimalism in Deep Learning

17.Gorilla: Large Language Model Connected with Massive APIs

18.Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

19.RWKV: Reinventing RNNs for the Transformer Era

20.C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

21.M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models

22.LIMA: Less Is More for Alignment

23.Any-to-Any Generation via Composable Diffusion

24.Evidence of Meaning in Language Models Trained on Programs

25.A Comprehensive Survey on Segment Anything Model for Vision and Beyond

26.Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold

27.SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

28.Transfer Visual Prompt Generator across LLMs

29.Unlimiformer: Long-Range Transformers with Unlimited Length Input

30.AutoML-GPT: Automatic Machine Learning with GPT

31.GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking

32.Shap-E: Generating Conditional 3D Implicit Functions

33.Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

34.PaLM 2 Technical Report

35.ImageBind: One Embedding Space To Bind Them All

点击下方链接可查看所有论文：

https://www.aminer.cn/topic/647daec0583c9a41be74e7b7

AMiner官网最新上线了ChatPaper功能，对话式文献知识库，用AI定义极简科研工作流，快来体验一下吧！！！