📚 文献库
Literature Library

MulTTiPop: A Multitrack Transcription 数据 (Data)set for Pop Music

MulTTiPop: A Multitrack Transcription Dataset for Pop Music

作者
Authors: Nathan Pruyne | Benjamin Stoler | William Chen | C... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 210 📚 5

Avoiding unsafe sets when training with Langevin Dynamics

作者
Authors: Adam M. Oberman 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 35 📚 17

The Key to Going Linear: 分析 (Analysis)-Driven Transformer Linearization

The Key to Going Linear: Analysis-Driven Transformer Linearization

作者
Authors: Anna Kuzina | Paul N. Whatmough | Babak Ehteshami ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 74 📚 13

Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

作者
Authors: Shervin Khalafi | Igor Krawczuk | Sergio Rozada | ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 165 📚 14

Interpretable Human-Label-Free Deep 学习 (Learning) for Real-Bogus 分类 (Classification) with Uncertaint...

Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantifi...

作者
Authors: Raphaël Bonnet-Guerrini | Bruno Sanchez | Dominiqu... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 206 📚 10

Cross-Audit Projection for 模型 (Model) Risk 预测 (Prediction)

Cross-Audit Projection for Model Risk Prediction

作者
Authors: Yijian Huang 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 223 📚 27

The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry

作者
Authors: Yuan Yuan 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 84 📚 14

Language-Critique Imitation 学习 (Learning) from Suboptimal Demonstrations

Language-Critique Imitation Learning from Suboptimal Demonstrations

作者
Authors: Chih-Han Yang | Dai-Jie Wu | Yun-Ping Huang | Ping... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 168 📚 26

Random Reshuffling Dominates Stochastic Gradient Descent

作者
Authors: Zijian Liu 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 119 📚 22

Freeform Preference 学习 (Learning) for Robotic Manipulation

Freeform Preference Learning for Robotic Manipulation

作者
Authors: Marcel Torne | Anubha Mahajan | Abhijnya Bhat | Ch... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 205 📚 10

Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation...

Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation...

作者
Authors: Subramanyam Sahoo | Aman Chadha | Vinija Jain | Di... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 186 📚 3

How Width and 数据 (Data) Shape Generalization Scaling Laws in Quadratic 神经网络 (Neural Network)s

How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks

作者
Authors: Julius Girardin | Emanuele Troiani | Yizhou Xu | V... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 45 📚 8

Surprises in Proper Positive-Only 学习 (Learning)

Surprises in Proper Positive-Only Learning

作者
Authors: Shai Ben-David | Farnam Mansouri | Anay Mehrotra |... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 105 📚 23

All you need is log

作者
Authors: Akshay Balsubramani 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 143 📚 17

When are likely answers right? On Sequence Probability and Correctness in LLMs

作者
Authors: Johannes Zenn | Jonas Geiping 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 66 📚 1

Reinforcement 学习 (Learning) without Ground-Truth Solutions can Improve LLMs

Reinforcement Learning without Ground-Truth Solutions can Improve LLMs

作者
Authors: Yingyu Lin | Qiyue Gao | Nikki Lijing Kuang | Xunp... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 119 📚 28

Deviance-style normalization for jointly overdispersed counts

作者
Authors: Akshay Balsubramani 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 86 📚 1

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity

作者
Authors: Andrei Liviu Nicolicioiu | Mohammad Pezeshki | Aar... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 82 📚 16

Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment

作者
Authors: Jason Sulskis | Sathya Ravi 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 108 📚 7

学习 (Learning) Process Rewards via Success Visitation Matching for Efficient RL

Learning Process Rewards via Success Visitation Matching for Efficient RL

作者
Authors: Raymond Tsao | Andrew Wagenmaker | Sergey Levine 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 深度学习
Deep Learning

👁 217 📚 1