1. 一文可视化分析2025年8月arXiv机器学习前沿热点#

最新文章#

ICML 2026论文分享｜ClinTutor-R1：面向临床苏格拉底教学的一对多智能辅导模型 让大语言模型先读懂外部事件：一种文本增强与正则扩散对齐的多模态时序预测框架 智慧医疗顶级期刊论文分享｜ReclAIm：用于医学影像 AI 性能运维的多智能体框架

2026

10月 1篇

09月 12篇

08月 21篇

07月 13篇

06月 4篇

05月 9篇

04月 7篇

03月 4篇

02月 8篇

01月 17篇

2025年 134篇

2024年 148篇

2023年 72篇

2022年 1篇

上一篇： arXiv 2025年8月Artificial Intelligence领域研究热点探秘 下一篇： ICCV 2025论文分享｜一种快速生成更逼真3D动画数字人的模型

分类专栏#

Image 71 人工智能好书推荐16篇 Image 72 人工智能书单 Image 73 人工智能怎么学72篇 Image 74 如何用AI填报高考志愿5篇 Image 75 中学生学人工智能系列11篇 Image 76 大学新生的学习秘诀

展开全部Image 77收起Image 78

登录后您可以享受以下权益：

Image 79免费复制代码 Image 80和博主大V互动 Image 81下载海量资源 Image 82发动态/写文章/加入社区

×立即登录

评论Image 83

[](

成就一亿技术人!

拼手气红包 6.0元

还能输入 1000 个字符|博主筛选后可见

Image 84: 表情包插入表情

Image 85: 表情包代码片

来源：https://blog.csdn.net/audyxiao001/article/details/151901100

2. Artificial Intelligence Oct 2026#

Merieme Askour, Ayoub Merimi

1
Comments: PREPRINT - SUBMITTED TO JOURNAL OF SERVICE RESEARCH (JSR)
2

3
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2610.00663 [pdf, html, other] : Title: Backdoor Containment via Expert Quarantine and Shutdown in LLMs

1
Jianwei Li, Min-Seon Kim, Jung-Eun Kim
2

3
Comments: NeurIPS 2026
4

5
Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG)

arXiv:2610.00668 [pdf, html, other] : Title: A Simple Doxastic Deontic Logic for Norm-Guided Decision Making

1
Thorsten Engesser, Agata Ciabattoni
2

3
Comments: Manuscript accepted at PRIMA 2026. Includes an additional appendix with proofs [...] Jianwei Li, Jung-Eun Kim
4

5
Comments: NeurIPS 2026
6

7
Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG)

arXiv:2610.00700 [pdf, html, other] : Title: R-GroundBench: A Diagnostic Benchmark for R-Group Groundingin Markush Molecular Editing

1
Xin Wang, Zichuan Ying, Xinna Lin, Junqi Zhang, Hanyi Xiong, Tianyu Gao, Hairong Zhang, Qixiang Hua, Botian Shi, Zhenhailong Wang, Kaicheng Yu
2

3
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2610.00705 [pdf, html, other] : Title: Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving

1
Huiwen Yan, Kyriakos G. Vamvoudakis, Mushuang Liu [...] Timothée Lesort, Alejandra López de Aberasturi Gómez, Tristan Karch, Tom Veniat, Philippe Modard, Karl Tuyls, Ludovic Denoyer
2

3
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2610.00437 [pdf, html, other] : Title: JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces

1
Haoyang Su, Weiran Huang
2

3
Subjects: Artificial Intelligence (cs.AI)

arXiv:2610.00447 [pdf, html, other] : Title: Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation

1
Anson Y. Lam, Shuqing Li, Michael R. Lyu
2

3
Comments: 26 pages, 6 figures
4

5
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Multimedia (cs.MM)

来源：https://arxiv.org/list/cs.AI/current

3. arXivDaily每日学术速递，同步arXiv全量数据，AI总结、翻译，覆盖人工智能、机器人、计算机、金融、统计学、数学、物理学、生物学、经济学、电气&系统等方向。#

URL PDF HTML 收藏

2610.02161 2026-10-02 cs.RO cs.AI 新提交

4. Machine Learning#

Comments: Website and code: this https URL

1
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

arXiv:2610.02098 [pdf, html, other] : Title: Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability

1
Chuqin Geng, Li Zhang, Haolin Ye, Mark Zhang, Luke Zhang, Xujie Si
2

3
Comments: 34 pages, 2 figures
4

5
Subjects: Machine Learning (cs.LG)

arXiv:2610.02067 [pdf, html, other] : Title: Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA

1
Zailong Tian, Yanzhe Chen, Zhuoheng Han, Houfeng Wang, Lizi Liao
2

3
Subjects: Machine Learning (cs.LG)

arXiv:2610.02058 [pdf, html, other] : Title: Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs […] Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

arXiv:2610.01831 [pdf, html, other] : Title: Pooling Helps, Learned Weighting Hurts In-Context: Decomposing Group Attention

1
Michael Fore, James Mason Inder, Mrishika Nair, Praneetha Vaddamanu, Sharlina Keshava
2

3
Subjects: Machine Learning (cs.LG)

arXiv:2610.01827 [pdf, html, other] : Title: Scientific Discovery under Validation Congestion via Multi-Fidelity Pairwise Rankings

1
Kevin Tirta Wijaya, Alston Lo, Michael Sun, Wojciech Matusik, Vahid Babaei
2

3
Subjects: Machine Learning (cs.LG)

arXiv:2610.01821 [pdf, html, other] : Title: Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models […] archive

Press Enter to search · Advanced search

Fri, 2 Oct 2026 (showing first 50 of 430 entries )#

arXiv:2610.02199 [pdf, html, other] : Title: TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning

1
Jichao Jiang (1), Cristian McGee (1), El Houcine Bergou (2), Hanqin Cai (1), Aritra Dutta (1) ((1) University of Central Florida, (2) Mohammed VI Polytechnic University)
2

3
Comments: 24 pages, 7 figures, 10 tables. Code available at this https URL

来源：https://arxiv.org/list/cs.LG/recent

5. Artificial Intelligence#

arXiv:2610.01513 [pdf, html, other] : Title: Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning

1
Jude Waide, Robert Lieck
2

3
Comments: Accepted at ICML 2026 Workshop on Decision-Making from Offline Datasets to Online Adaptation: Black-Box Optimization to Reinforcement Learning
4

5
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2610.01509 [pdf, html, other] : Title: Sharpening Tax in Post-Training

1
Changdae Oh, Qi Zeng, Qi Qi, Andrey Zhmoginov, Deren Lei, Yun He, Hoang Phan, Hangoo Kang, Azalia Mirhoseini, Sharon Li
2

3
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) [...] archive

Press Enter to search · Advanced search

Fri, 2 Oct 2026 (showing first 50 of 381 entries )#

arXiv:2610.02202 [pdf, html, other] : Title: ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

1
Sohyeon Kim, Yoonho Lee, Bo Liu, Dayoon Ko, Rulin Shao, Seungone Kim, Graham Neubig, Pang Wei Koh, Aakanksha Chowdhery, Akari Asai, Omar Khattab, Yejin Choi, Gunhee Kim, Chelsea Finn
2

3
Comments: 57 pages [...] Comments: 18 pages, 6 figures
4

5
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

arXiv:2610.02074 [pdf, html, other] : Title: Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints

1
Abid Mohamed Nadhir, Ahmad Al Hanbali, Beggas Mounir
2

3
Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)

arXiv:2610.02072 [pdf, html, other] : Title: PyPottery: an AI-powered end-to-end suite for pottery processing and publication

1
Lorenzo Cardarelli
2

3
Subjects: Artificial Intelligence (cs.AI)

arXiv:2610.02070 [pdf, html, other] : Title: Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval

1
Arman Behnam, Binghui Wang

来源：https://arxiv.org/list/cs.AI/recent