📚 文献库
Literature Library

特工管制议定书:特工行动入境管制

Agent Control Protocol: Admission Control for Agent Actions

作者
Authors: Marcelo Fernandez 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 392 📚 27

学生对AI道德和社会影响的看法

Student views in AI Ethics and Social Impact

作者
Authors: Tudor-Dan Mihoc|Manuela-Andreea Petrescu|Emilia-Lo... 期刊
Journal: Proceedings of the 17th International Conference on Computer Supported Education 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 443 📚 0

ProRL代理:推出多种LLM代理的RL培训服务

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

作者
Authors: Hao Zhang|Mingjie Liu|Shaokun Zhang|Songyang Han|J... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 263 📚 9

LLM能产生有趣的数学研究问题吗?

Can LLM generate interesting mathematical research problems?

作者
Authors: Xiaoyang Chen|Xiang Jiang 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 140 📚 44

dTRPO: Trajectory Reduction in Policy 优化 (Optimization) of Diffusion Large Language 模型 (Model)s

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models

作者
Authors: Wenxuan Zhang|Lemeng Wu|Changsheng Zhao|Ernie Chan... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 279 📚 30

Perceptio: Perception Enhanced Vision Language 模型 (Model)s via Spatial Token Generation

Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation

作者
Authors: Yuchen Li|Amanmeet Garg|Shalini Chaudhuri|Rui Zhao... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 87 📚 41

Functional Subspace Watermarking for Large Language 模型 (Model)s

Functional Subspace Watermarking for Large Language Models

作者
Authors: Zikang Ding|Junhao Li|Suling Wu|Junchi Yao|Hongbo ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 232 📚 5

米:dm K 2. 5 Pro (英语)

Mi:dm K 2.5 Pro

作者
Authors: KT Tech innovation Group 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 405 📚 5

关于通过思想理论推进人工智能的第二次讲习班会议记录

Proceedings of the 2nd Workshop on Advancing Artificial Intelligence through Theory of Mind

作者
Authors: Nitay Alon|Joseph M. Barnby|Reuth Mirsky|Stefan Sa... 期刊
Journal: Artificial Intelligence 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 591 📚 27

点到-3D: 结构- 软件 三维生成与点云前传

Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors

作者
Authors: Jiatong Xia|Zicheng Duan|Anton van den Hengel|Ling... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 446 📚 40

A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion 模型 (Model)s

A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models

作者
Authors: Duc Hao Pham|Van Duy Truong|Duy Khanh Dinh|Tien Cu... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 410 📚 22

ClawTrap:基于MITM的实时世界开放法律安全评价红色团队框架

ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation

作者
Authors: Haochen Zhao|Shaoyang Cui 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 340 📚 47

NeuroGame Transformer: Gibbs-Inspired Attention Driven by Game Theory and 统计 (Statistical) Physics

NeuroGame Transformer: Gibbs-Inspired Attention Driven by Game Theory and Statistical Physics

作者
Authors: Djamel Bouchaffra|Fayçal Ykhlef|Hanene Azzag|Musta... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 570 📚 43

Quantitative Introspection in Language 模型 (Model)s: Tracking Internal States Across Conversation

Quantitative Introspection in Language Models: Tracking Internal States Across Conversation

作者
Authors: Nicolas Martorell 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 455 📚 26

MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language 模型 (Model)

MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model

作者
Authors: Youngwan Lee|Soojin Jang|Yoorhim Cho|Seunghwan Lee... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 456 📚 47

数学对象上的理由:政策奖励模型和测试时间汇总

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

作者
Authors: Pranjal Aggarwal|Marjan Ghazvininejad|Seungone Kim... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 307 📚 41

ChatGPT指出

Geography According to ChatGPT -- How Generative AI Represents and Reasons about Geography

作者
Authors: Krzysztof Janowicz|Gengchen Mai|Rui Zhu|Song Gao|Z... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 80 📚 23

Evaluating LLM-Generated Lessons from the Language 学习 (Learning) Students' Perspective: A Short Case...

Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Stud...

作者
Authors: Carlos Rafael Catalan|Patricia Nicole Monderin|Lhe... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 88 📚 49

FinTrade Bench:有限责任公司的财务理由基准

FinTradeBench: A Financial Reasoning Benchmark for LLMs

作者
Authors: Yogesh Agrawal, Aniruddha Dutta, Md Mahadi Hasan, ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 311 📚 50

F2LLM-v2:多语言世界的包容性、表演性和高效嵌入

F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

作者
Authors: Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wan... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 人工智能
Artificial Intelligence

👁 346 📚 40