arXiv 高引趋势论文
PAPERS论文与趋势从五个角度看 AI 技术动向：arXiv 高引趋势论文（看技术底座）、HuggingFace 每日精选论文（看当天热点）、arXiv 最新提交（看前沿动向）、HuggingFace 趋势榜（看生态热度）、社区热门 Issue（看工程侧真实动向）。五个分区各有独立地址与数据源。
数据日期
2026-10-27
数据时间 2026-10-27 19:00 · 检索命中 125 篇
本批聚合 30 篇 AI 高引趋势论文，合计被引 52,032 次，单篇最高 9,452 次；覆盖 16 个会议 / 期刊、6 个年份。列表按引用量排序，可用于判断某个方向的技术底座来自哪几篇工作。
本批论文
30
检索命中 125 篇后取前 30
合计被引
52,032
Semantic Scholar 引用口径
单篇最高被引
9,452
本批第一名
覆盖会议 / 期刊
16
含 arXiv 预印本
年份跨度
2020–2025
按发表年份
筛选与排序
arXiv 高引趋势论文年份、会议与作者分布
6 个年份发表年份分布
高产会议 / 期刊
arXiv.org
8 篇本批高引论文的发表会议 / 期刊
本批高引论文的发表会议 / 期刊
本批高引论文的发表会议 / 期刊
本批高引论文的发表会议 / 期刊
本批高引论文的发表会议 / 期刊
本批高引论文的发表会议 / 期刊
高产作者
Joseph E. Gonzalez
2 篇在本批论文中出现的篇数
Woosuk Kwon
1 篇在本批论文中出现的篇数
Zhuo-Han Li
1 篇在本批论文中出现的篇数
Si-Yuan Zhuang
1 篇在本批论文中出现的篇数
Ying Sheng
1 篇在本批论文中出现的篇数
Lian-Min Zheng
1 篇在本批论文中出现的篇数
高引趋势论文
显示 30 / 30 篇| 排名 | 论文 | 年份 | 会议 / 期刊 | 被引 | 研究领域 | 摘要（截断） | 原文 | 预印本 |
|---|---|---|---|---|---|---|---|---|
| 1 | Efficient Memory Management for Large Language Model Serving with PagedAttention Woosuk Kwon、Zhuo-Han Li、Si-Yuan Zhuang 等 8 人 · Symposium on Operating Systems Principles | 2023 | Symposium on Operating Systems Principles | 9,452 | Computer Science | High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV c… | Semantic Scholar → | arXiv → |
| 2 | Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback Yuntao Bai、Andy Jones、Kamal Ndousse 等 8 人 · arXiv.org | 2022 | arXiv.org | 4,423 | Computer Science | We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants. We find this alignment train… | Semantic Scholar → | arXiv → |
| 3 | A survey on large language model based autonomous agents Lei Wang、Chengbang Ma、Xue-Yang Feng 等 8 人 · Frontiers of Computer Science | 2023 | Frontiers of Computer Science | 4,244 | Computer Science | Autonomous agents have long been a research focus in academic and industry communities. Previous research often focuses on training agents with limited knowledge within isolated en… | Semantic Scholar → | arXiv → |
| 4 | The Rise and Potential of Large Language Model Based Agents: A Survey Zhiheng Xi、Wen-Xiang Chen、Xin Guo 等 8 人 · arXiv.org | 2023 | arXiv.org | 2,168 | Computer Science | For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI a… | Semantic Scholar → | arXiv → |
| 5 | DiffWave: A Versatile Diffusion Model for Audio Synthesis Zhifeng Kong、Wei Ping、Jiaji Huang 等 5 人 · International Conference on Learning Representations | 2020 | International Conference on Learning Representations | 2,137 | Computer Science、Engineering、Mathematics | In this work, we propose DiffWave, a versatile Diffusion probabilistic model for conditional and unconditional Waveform generation. The model is non-autoregressive, and converts th… | Semantic Scholar → | arXiv → |
| 6 | CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society G. Li、Hasan Hammoud、Hani Itani 等 5 人 · Neural Information Processing Systems | 2023 | Neural Information Processing Systems | 2,087 | Computer Science | The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conver… | Semantic Scholar → | arXiv → |
| 7 | DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence Daya Guo、Qi-Hao Zhu、De-Jian Yang 等 8 人 · arXiv.org | 2024 | arXiv.org | 1,994 | Computer Science | The rapid development of large language models has revolutionized code intelligence in software development. However, the predominance of closed-source models has restricted extens… | Semantic Scholar → | arXiv → |
| 8 | Gorilla: Large Language Model Connected with Massive APIs Shishir G. Patil、Tianjun Zhang、Xin Wang 等 4 人 · Neural Information Processing Systems | 2023 | Neural Information Processing Systems | 1,798 | Computer Science | Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesi… | Semantic Scholar → | arXiv → |
| 9 | CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis E. Nijkamp、Bo Pang、Hiroaki Hayashi 等 8 人 · International Conference on Learning Representations | 2022 | International Conference on Learning Representations | 1,643 | Computer Science | Program synthesis strives to generate a computer program as a solution to a given problem specification, expressed with input-output examples or natural language descriptions. The… | Semantic Scholar → | arXiv → |
| 10 | BloombergGPT: A Large Language Model for Finance Shijie Wu、Ozan Irsoy、Steven Lu 等 8 人 · arXiv.org | 2023 | arXiv.org | 1,571 | Computer Science、Economics | The use of NLP in the realm of financial technology is broad and complex, with applications ranging from sentiment analysis and named entity recognition to question answering. Larg… | Semantic Scholar → | arXiv → |
| 11 | Human Motion Diffusion Model Guy Tevet、Sigal Raab、Brian Gordon 等 6 人 · International Conference on Learning Representations | 2022 | International Conference on Learning Representations | 1,495 | Computer Science | Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitiv… | Semantic Scholar → | arXiv → |
| 12 | A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly Yi-Fan Yao、Jinhao Duan、Kai-Di Xu 等 6 人 · High Confid. Comput. | 2023 | High Confid. Comput. | 1,393 | Computer Science | Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized natural language understanding and generation. They possess deep language comprehension, human-like text… | Semantic Scholar → | arXiv → |
| 13 | Large Language Model based Multi-Agents: A Survey of Progress and Challenges Taicheng Guo、Xiu-Ying Chen、Ya-Qi Wang 等 8 人 · International Joint Conference on Artificial Intelligence | 2024 | International Joint Conference on Artificial Intelligence | 1,294 | Computer Science | Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to their notable capabilities in planning and reasoning, LLMs have been utilized as… | Semantic Scholar → | arXiv → |
| 14 | Accelerating Large Language Model Decoding with Speculative Sampling Charlie Chen、Sebastian Borgeaud、Geoffrey Irving 等 6 人 · arXiv.org | 2023 | arXiv.org | 1,238 | Computer Science | We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies o… | Semantic Scholar → | arXiv → |
| 15 | DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Yinmin Zhong、Sheng-Yu Liu、Junda Chen 等 8 人 · USENIX Symposium on Operating Systems Design and Implementation | 2024 | USENIX Symposium on Operating Systems Design and Implementation | 1,137 | Computer Science | DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two pha… | Semantic Scholar → | arXiv → |
| 16 | Galactica: A Large Language Model for Science Ross Taylor、Marcin Kardas、Guillem Cucurull 等 8 人 · arXiv.org | 2022 | arXiv.org | 1,127 | Computer Science、Mathematics | Information overload is a major obstacle to scientific progress. The explosive growth in scientific literature and data has made it ever harder to discover useful insights in a lar… | Semantic Scholar → | arXiv → |
| 17 | Vector Quantized Diffusion Model for Text-to-Image Synthesis S. Gu、Dong Chen、J. Bao 等 8 人 · Computer Vision and Pattern Recognition | 2021 | Computer Vision and Pattern Recognition | 1,123 | Computer Science | We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose laten… | Semantic Scholar → | arXiv → |
| 18 | MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model Mingyuan Zhang、Zhongang Cai、Liang Pan 等 7 人 · IEEE Transactions on Pattern Analysis and Machine Intelligence | 2022 | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1,121 | Computer Science、Medicine | Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent moti… | Semantic Scholar → | arXiv → |
| 19 | LISA: Reasoning Segmentation via Large Language Model Xin Lai、Zhuo-Tao Tian、Yu-Kang Chen 等 7 人 · Computer Vision and Pattern Recognition | 2023 | Computer Vision and Pattern Recognition | 1,107 | Computer Science | Although perception systems have made remarkable ad-vancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objec… | Semantic Scholar → | arXiv → |
| 20 | Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback Stephen Casper、Xander Davies、Claudia Shi 等 8 人 · Trans. Mach. Learn. Res. | 2023 | Trans. Mach. Learn. Res. | 995 | Computer Science | Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of… | Semantic Scholar → | arXiv → |
| 21 | OpenAssistant Conversations - Democratizing Large Language Model Alignment Andreas Kopf、Yannic Kilcher、Dimitri von Rütte 等 8 人 · Neural Information Processing Systems | 2023 | Neural Information Processing Systems | 974 | Computer Science | Aligning large language models (LLMs) with human preferences has proven to drastically improve usability and has driven rapid adoption as demonstrated by ChatGPT. Alignment techniq… | Semantic Scholar → | arXiv → |
| 22 | Diffusion Model Alignment Using Direct Preference Optimization Bram Wallace、Mei-Hua Dang、Rafael Rafailov 等 8 人 · Computer Vision and Pattern Recognition | 2023 | Computer Vision and Pattern Recognition | 961 | Computer Science | Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' prefe… | Semantic Scholar → | arXiv → |
| 23 | TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation Keqin Bao、Jizhi Zhang、Yang Zhang 等 6 人 · ACM Conference on Recommender Systems | 2023 | ACM Conference on Recommender Systems | 921 | Computer Science | Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains, thereby prompting researchers to explore their potential for use in recommendation sys… | Semantic Scholar → | arXiv → |
| 24 | Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory Prateek Chhikara、Dev Khant、Saket Aryan 等 5 人 · European Conference on Artificial Intelligence | 2025 | European Conference on Artificial Intelligence | 836 | Computer Science | Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for mai… | Semantic Scholar → | arXiv → |
| 25 | The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets Samuel Marks、Max Tegmark · arXiv.org | 2023 | arXiv.org | 825 | Computer Science | Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is telling the t… | Semantic Scholar → | arXiv → |
| 26 | DiffusionDet: Diffusion Model for Object Detection Shoufa Chen、Pei Sun、Yi-Bing Song 等 4 人 · IEEE International Conference on Computer Vision | 2022 | IEEE International Conference on Computer Vision | 825 | Computer Science | We propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. During the training stage, object boxes… | Semantic Scholar → | arXiv → |
| 27 | ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge Yun-Xiang Li、Zihan Li、Kai Zhang 等 6 人 · Cureus | 2023 | Cureus | 807 | Medicine、Computer Science | Objective The primary aim of this research was to address the limitations observed in the medical knowledge of prevalent large language models (LLMs) such as ChatGPT, by creating a… | Semantic Scholar → | arXiv → |
| 28 | Safe RLHF: Safe Reinforcement Learning from Human Feedback Josef Dai、Xuehai Pan、Ruiyang Sun 等 8 人 · International Conference on Learning Representations | 2023 | International Conference on Learning Representations | 806 | Computer Science | With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tensio… | Semantic Scholar → | arXiv → |
| 29 | RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback Harrison Lee、Samrat Phatale、H. Mansoor 等 8 人 · International Conference on Machine Learning | 2023 | International Conference on Machine Learning | 767 | Computer Science | Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels… | Semantic Scholar → | arXiv → |
| 30 | MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning Jun Chen、Deyao Zhu、Xiaoqian Shen 等 8 人 · arXiv.org | 2023 | arXiv.org | 763 | Computer Science | Large language models have shown their remarkable capabilities as a general interface for various language-related applications. Motivated by this, we target to build a unified int… | Semantic Scholar → | arXiv → |
数据说明
收录口径按引用量排序论文元数据、引用量与会议 / 期刊归属按索引口径展示
数据日期2026-10-27候选 125 篇中取引用量最高的 30 篇
收录规模30 篇 · 合计被引 52,032单篇最高 9,452 次 · 16 个会议 / 期刊
年份跨度2020–2025引用量有先发优势，老论文天然更高
怎么用看技术底座判断某方向源自哪几篇工作，不做单篇强弱排序
常见问题
引用量高的论文就是更好的方案吗？
不是。引用量有很强的先发优势，2023 年的工作天然比 2025 年的新方法引用多得多。这张榜用来找某个方向的技术底座，不是给模型或方案排强弱。
怎么用它入门一个方向？
先按会议 / 年份和关键词筛，找出该方向被引最高的几篇奠基工作，再顺着作者与引用关系往下追；想看最新进展，去「arXiv 最新提交」那一栏。
会议 / 期刊字段为空是什么意思？
可能是仍是预印本，也可能是上游没有收录到发表信息。空不代表没发表，正式引用前请自行确认接收状态。
为什么榜上多是几年前的老论文？
引用需要时间累积，新论文很难一年内进高引榜。高引榜看「奠基」，最新动向看「arXiv 最新提交」，两者互补。
论文元数据、引用量与会议归属取自公开论文索引；引用量按各索引的统计口径展示。
