Cover Image

Residual Stream Analysis of Overfitting And Structural Disruptions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Quan, Zhou, Han, Wu, Wenquan, Wu, Hua, Su, Sen
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections
by: Peng, William, et al.
Published: (2026)

Overcoming Overfitting in Reinforcement Learning via Gaussian Process Diffusion Policy
by: Horprasert, Amornyos, et al.
Published: (2025)

Control of Overfitting with Physics
by: Kozyrev, Sergei V., et al.
Published: (2024)

Towards Mitigating Architecture Overfitting on Distilled Datasets
by: Zhong, Xuyang, et al.
Published: (2023)

Benign Overfitting in Adversarial Training for Vision Transformers
by: Zhang, Jiaming, et al.
Published: (2026)

How to Mitigate Overfitting in Weak-to-strong Generalization?
by: Shi, Junhao, et al.
Published: (2025)

Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology
by: Fernando, Jesseba, et al.
Published: (2026)

On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
by: Ye, Hao, et al.
Published: (2026)

Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection
by: Qian, Long, et al.
Published: (2024)

Detecting Generative Parroting through Overfitting Masked Autoencoders
by: Taghanaki, Saeid Asgari, et al.
Published: (2024)

The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference
by: Qasim, Kaleem Ullah, et al.
Published: (2026)

Residual Stream Duality in Modern Transformer Architectures
by: Zhang, Yifan
Published: (2026)

Residual Cross-Attention Transformer-Based Multi-User CSI Feedback with Deep Joint Source-Channel Coding
by: Zhang, Hengwei, et al.
Published: (2025)

LoRA Dropout as a Sparsity Regularizer for Overfitting Control
by: Lin, Yang, et al.
Published: (2024)

A Classical View on Benign Overfitting: The Role of Sample Size
by: Park, Junhyung, et al.
Published: (2025)

DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting
by: Zhang, Yeran, et al.
Published: (2026)

Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model
by: Niu, Peisong, et al.
Published: (2025)

DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting
by: Liang, Daojun, et al.
Published: (2025)

Benign Overfitting for Regression with Trained Two-Layer ReLU Networks
by: Park, Junhyung, et al.
Published: (2024)

Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation
by: Choi, Yoonhyuk, et al.
Published: (2022)

From Overfitting to Reliability: Introducing the Hierarchical Approximate Bayesian Neural Network
by: Amirkhanian, Hayk, et al.
Published: (2025)

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
by: Hui, Tingfeng, et al.
Published: (2024)

Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback
by: Zhou, Quan, et al.
Published: (2025)

Learning from Streaming Data when Users Choose
by: Su, Jinyan, et al.
Published: (2024)

AdaResNet: Enhancing Residual Networks with Dynamic Weight Adjustment for Improved Feature Integration
by: Su, Hong
Published: (2024)

mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
by: Koh, Woosung, et al.
Published: (2026)

Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
by: Li, Jiping, et al.
Published: (2025)

PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
by: Zhang, Junru, et al.
Published: (2026)

Fair Streaming Feature Selection
by: Duan, Zhangling, et al.
Published: (2024)

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
by: Liu, Shuang, et al.
Published: (2025)

A Theoretical Analysis of Discrete Flow Matching Generative Models
by: Su, Maojiang, et al.
Published: (2025)

Renaissance of RNNs in Streaming Clinical Time Series: Compact Recurrence Remains Competitive with Transformers
by: Tong, Ran, et al.
Published: (2025)

Extension OL-MDISF: Online Learning from Mix-Typed, Drifted, and Incomplete Streaming Features
by: Zhuo, Shengda, et al.
Published: (2025)

When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs
by: Xiao, Shuai, et al.
Published: (2026)

Cooperative Advisory Residual Policies for Congestion Mitigation
by: Hasan, Aamir, et al.
Published: (2024)

GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction
by: Kong, Weiyang, et al.
Published: (2025)

Contrastive Residual Energy Test-time Adaptation
by: Han, Yewon, et al.
Published: (2025)

Explaining Model Overfitting in CNNs via GMM Clustering
by: Dou, Hui, et al.
Published: (2024)

How Ensemble Learning Balances Accuracy and Overfitting: A Bias-Variance Perspective on Tabular Data
by: Mohammad, Zubair Ahmed
Published: (2025)

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
by: Qiao, Dan, et al.
Published: (2024)