Imagen de Portada

Stability of In-Context Learning: A Spectral Coverage Perspective

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Tongxi, Xia, Zhuoyang
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
por: Wang, Tongxi, et al.
Publicado: (2026)

Sharp Spectral Thresholds for Logit Fixed Points
por: Wang, Tongxi
Publicado: (2026)

UCS: Estimating Unseen Coverage for Improved In-Context Learning
por: Xin, Jiayi, et al.
Publicado: (2026)

Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification
por: Xia, Yutong, et al.
Publicado: (2024)

Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
por: Wu, Tongxi, et al.
Publicado: (2026)

Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
por: Falck, Fabian, et al.
Publicado: (2024)

The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
por: Zhang, Hongtao, et al.
Publicado: (2026)

Brewing Knowledge in Context: Distillation Perspectives on In-Context Learning
por: Li, Chengye, et al.
Publicado: (2025)

Addressing Graph Heterogeneity and Heterophily from A Spectral Perspective
por: Lu, Kangkang, et al.
Publicado: (2024)

Ultrasound Vision-Language Alignment via Contrastive Learning
por: Lyu, Zhuoyang, et al.
Publicado: (2026)

A Bayesian Perspective on the Role of Epistemic Uncertainty for Delayed Generalization in In-Context Learning
por: Qchohi, Abdessamed, et al.
Publicado: (2026)

Space Syntax-guided Post-training for Residential Floor Plan Generation
por: Jiang, Zhuoyang, et al.
Publicado: (2026)

Exact Finite-Sample Variance Decomposition of Subagging: A Spectral Filtering Perspective
por: Su, Ye, et al.
Publicado: (2026)

Optimizing FPGA and Wafer Test Coverage with Spatial Sampling and Machine Learning
por: WeiQuan, Wang, et al.
Publicado: (2025)

Spectral Thresholds for Identifiability and Stability:Finite-Sample Phase Transitions in High-Dimensional Learning
por: Huang, William Hao-Cheng
Publicado: (2025)

Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspective
por: Zhang, Haoyu, et al.
Publicado: (2025)

Learning from Heterophilic Graphs: A Spectral Theory Perspective on the Impact of Self-Loops and Parallel Edges
por: Bose, Kushal, et al.
Publicado: (2025)

Spectral Algorithms on Manifolds through Diffusion
por: Xia, Weichun, et al.
Publicado: (2024)

DynFrs: An Efficient Framework for Machine Unlearning in Random Forest
por: Wang, Shurong, et al.
Publicado: (2024)

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
por: Huang, Jiawei, et al.
Publicado: (2025)

Federated Learning and Trajectory Compression for Enhanced AIS Coverage
por: Gräupl, Thomas, et al.
Publicado: (2025)

Optimizing Coverage and Difficulty in Reinforcement Learning for Quiz Composition
por: Silva, Ricardo Pedro Querido Andrade, et al.
Publicado: (2026)

Optimal Policy Learning under Budget and Coverage Constraints
por: Cerulli, Giovanni
Publicado: (2026)

Coverage Improvement and Fast Convergence of On-policy Preference Learning
por: Kim, Juno, et al.
Publicado: (2026)

Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
por: Dong, Yuxin, et al.
Publicado: (2025)

Spectral Audit of In-Context Operator Networks
por: Gao, Zhiwei, et al.
Publicado: (2026)

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
por: Zhang, Chenxiang, et al.
Publicado: (2025)

CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification
por: Xu, Jiacheng, et al.
Publicado: (2025)

Adaptive Hopfield Network: Rethinking Similarities in Associative Memory
por: Wang, Shurong, et al.
Publicado: (2025)

Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective
por: Kwon, Soo Min, et al.
Publicado: (2025)

A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets
por: Kubo, Akihiro, et al.
Publicado: (2026)

Offline Constrained Reinforcement Learning under Partial Data Coverage
por: Ko, Seokmin, et al.
Publicado: (2025)

Training-Conditional Coverage Bounds for Uniformly Stable Learning Algorithms
por: Pournaderi, Mehrdad, et al.
Publicado: (2024)

PAC Guarantees for Reinforcement Learning: Sample Complexity, Coverage, and Structure
por: Steier, Joshua
Publicado: (2026)

Generalized Coverage for More Robust Low-Budget Active Learning
por: Bae, Wonho, et al.
Publicado: (2024)

Toward a Better Understanding of Fourier Neural Operators from a Spectral Perspective
por: Qin, Shaoxiang, et al.
Publicado: (2024)

Learning Curves and Benign Overfitting of Spectral Algorithms in Large Dimensions
por: Lu, Weihao, et al.
Publicado: (2026)

Understanding Emergent In-Context Learning from a Kernel Regression Perspective
por: Han, Chi, et al.
Publicado: (2023)

Active Learning For Repairable Hardware Systems With Partial Coverage
por: Potter, Michael, et al.
Publicado: (2025)

Asymmetric Learning for Spectral Graph Neural Networks
por: Liu, Fangbing, et al.
Publicado: (2024)