Image de couverture de livre

Stability of In-Context Learning: A Spectral Coverage Perspective

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Tongxi, Xia, Zhuoyang
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
par: Wang, Tongxi, et autres
Publié: (2026)

Sharp Spectral Thresholds for Logit Fixed Points
par: Wang, Tongxi
Publié: (2026)

UCS: Estimating Unseen Coverage for Improved In-Context Learning
par: Xin, Jiayi, et autres
Publié: (2026)

Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification
par: Xia, Yutong, et autres
Publié: (2024)

Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
par: Wu, Tongxi, et autres
Publié: (2026)

Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
par: Falck, Fabian, et autres
Publié: (2024)

The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
par: Zhang, Hongtao, et autres
Publié: (2026)

Brewing Knowledge in Context: Distillation Perspectives on In-Context Learning
par: Li, Chengye, et autres
Publié: (2025)

Addressing Graph Heterogeneity and Heterophily from A Spectral Perspective
par: Lu, Kangkang, et autres
Publié: (2024)

Ultrasound Vision-Language Alignment via Contrastive Learning
par: Lyu, Zhuoyang, et autres
Publié: (2026)

A Bayesian Perspective on the Role of Epistemic Uncertainty for Delayed Generalization in In-Context Learning
par: Qchohi, Abdessamed, et autres
Publié: (2026)

Space Syntax-guided Post-training for Residential Floor Plan Generation
par: Jiang, Zhuoyang, et autres
Publié: (2026)

Exact Finite-Sample Variance Decomposition of Subagging: A Spectral Filtering Perspective
par: Su, Ye, et autres
Publié: (2026)

Optimizing FPGA and Wafer Test Coverage with Spatial Sampling and Machine Learning
par: WeiQuan, Wang, et autres
Publié: (2025)

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

Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspective
par: Zhang, Haoyu, et autres
Publié: (2025)

Learning from Heterophilic Graphs: A Spectral Theory Perspective on the Impact of Self-Loops and Parallel Edges
par: Bose, Kushal, et autres
Publié: (2025)

Spectral Algorithms on Manifolds through Diffusion
par: Xia, Weichun, et autres
Publié: (2024)

DynFrs: An Efficient Framework for Machine Unlearning in Random Forest
par: Wang, Shurong, et autres
Publié: (2024)

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
par: Huang, Jiawei, et autres
Publié: (2025)

Federated Learning and Trajectory Compression for Enhanced AIS Coverage
par: Gräupl, Thomas, et autres
Publié: (2025)

Optimizing Coverage and Difficulty in Reinforcement Learning for Quiz Composition
par: Silva, Ricardo Pedro Querido Andrade, et autres
Publié: (2026)

Optimal Policy Learning under Budget and Coverage Constraints
par: Cerulli, Giovanni
Publié: (2026)

Coverage Improvement and Fast Convergence of On-policy Preference Learning
par: Kim, Juno, et autres
Publié: (2026)

Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
par: Dong, Yuxin, et autres
Publié: (2025)

Spectral Audit of In-Context Operator Networks
par: Gao, Zhiwei, et autres
Publié: (2026)

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
par: Zhang, Chenxiang, et autres
Publié: (2025)

CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification
par: Xu, Jiacheng, et autres
Publié: (2025)

Adaptive Hopfield Network: Rethinking Similarities in Associative Memory
par: Wang, Shurong, et autres
Publié: (2025)

Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective
par: Kwon, Soo Min, et autres
Publié: (2025)

A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets
par: Kubo, Akihiro, et autres
Publié: (2026)

Offline Constrained Reinforcement Learning under Partial Data Coverage
par: Ko, Seokmin, et autres
Publié: (2025)

Training-Conditional Coverage Bounds for Uniformly Stable Learning Algorithms
par: Pournaderi, Mehrdad, et autres
Publié: (2024)

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

Generalized Coverage for More Robust Low-Budget Active Learning
par: Bae, Wonho, et autres
Publié: (2024)

Toward a Better Understanding of Fourier Neural Operators from a Spectral Perspective
par: Qin, Shaoxiang, et autres
Publié: (2024)

Learning Curves and Benign Overfitting of Spectral Algorithms in Large Dimensions
par: Lu, Weihao, et autres
Publié: (2026)

Understanding Emergent In-Context Learning from a Kernel Regression Perspective
par: Han, Chi, et autres
Publié: (2023)

Active Learning For Repairable Hardware Systems With Partial Coverage
par: Potter, Michael, et autres
Publié: (2025)

Asymmetric Learning for Spectral Graph Neural Networks
par: Liu, Fangbing, et autres
Publié: (2024)