:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Nordby, Erik, Pais, Tasha, Parrack, Aviel
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2604.13386
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities
by: Nordby, Ross
Published: (2025)

Benchmarking Deception Probes via Black-to-White Performance Boosts
by: Parrack, Avi, et al.
Published: (2025)

The Disparate Benefits of Deep Ensembles
by: Schweighofer, Kajetan, et al.
Published: (2024)

Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
by: Njaradi, Valentina, et al.
Published: (2026)

Probe-then-Commit Multi-Objective Bandits: Theoretical Benefits of Limited Multi-Arm Feedback
by: Shi, Ming
Published: (2026)

On the Benefits of Rank in Attention Layers
by: Amsel, Noah, et al.
Published: (2024)

SiamTST: A Novel Representation Learning Framework for Enhanced Multivariate Time Series Forecasting applied to Telco Networks
by: Kristoffersen, Simen, et al.
Published: (2024)

LayerMatch: Do Pseudo-labels Benefit All Layers?
by: Liang, Chaoqi, et al.
Published: (2024)

Joint Optimization of Piecewise Linear Ensembles
by: Raymond, Matt, et al.
Published: (2024)

Improved Regret of Linear Ensemble Sampling
by: Lee, Harin, et al.
Published: (2024)

An Ensemble Classification Approach in A Multi-Layered Large Language Model Framework for Disease Prediction
by: Hamdi, Ali, et al.
Published: (2025)

Gated Uncertainty-Aware Runtime Dual Invariants for Neural Signal-Controlled Robotics
by: Kim, Tasha, et al.
Published: (2025)

Scaling Motion Forecasting Models with Ensemble Distillation
by: Ettinger, Scott, et al.
Published: (2024)

The Law of Multi-Model Collaboration: Scaling Limits of Model Ensembling for Large Language Models
by: Lu, Dakuan, et al.
Published: (2025)

ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models
by: Parkinson, Suzanna, et al.
Published: (2023)

Linear Mode Connectivity in Differentiable Tree Ensembles
by: Kanoh, Ryuichi, et al.
Published: (2024)

What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
by: Heo, Eunwoo, et al.
Published: (2026)

Hardware Aware Ensemble Selection for Balancing Predictive Accuracy and Cost
by: Maier, Jannis, et al.
Published: (2024)

Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size
by: Kukreja, Dikshant, et al.
Published: (2026)

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
by: Oldfield, James, et al.
Published: (2025)

Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
by: Boharon, Daniel, et al.
Published: (2026)

Balancing Accuracy and Speed: A Multi-Fidelity Ensemble Kalman Filter with a Machine Learning Surrogate Model
by: van der Voort, Jeffrey, et al.
Published: (2025)

LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles
by: Ebrahimpour-Boroojeny, Ali, et al.
Published: (2024)

Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
by: Tomihari, Akiyoshi, et al.
Published: (2024)

Boosting the Accuracy of Stock Market Prediction via Multi-Layer Hybrid MTL Structure
by: Hong, Yuxi
Published: (2025)

On Extending Semantic Abstraction for Efficient Search of Hidden Objects
by: Pais, Tasha, et al.
Published: (2025)

Ensembles at Any Cost? Accuracy-Energy Trade-offs in Recommender Systems
by: Nitschke, Jannik, et al.
Published: (2026)

Multi-Objective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural Networks
by: Bernardelli, Ambrogio Maria, et al.
Published: (2022)

Integrating Random Forests and Generalized Linear Models for Improved Accuracy and Interpretability
by: Agarwal, Abhineet, et al.
Published: (2023)

Detecting Strategic Deception Using Linear Probes
by: Goldowsky-Dill, Nicholas, et al.
Published: (2025)

Enhancing Predictive Accuracy in Pharmaceutical Sales Through An Ensemble Kernel Gaussian Process Regression Approach
by: Mirshekari, Shahin, et al.
Published: (2024)

Scaling Embedding Layers in Language Models
by: Yu, Da, et al.
Published: (2025)

Layer-wise Linear Mode Connectivity
by: Adilova, Linara, et al.
Published: (2023)

Improving World Models using Deep Supervision with Linear Probes
by: Zahorodnii, Andrii
Published: (2025)

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
by: Gaitonde, Jason, et al.
Published: (2026)

Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks
by: Zhang, Han, et al.
Published: (2024)

AutoScale: Linear Scalarization Guided by Multi-Task Optimization Metrics
by: Yang, Yi, et al.
Published: (2025)

Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA
by: Jin, Xiao, et al.
Published: (2026)

Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
by: Pang, Tianyu, et al.
Published: (2026)

Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenders
by: Zhao, Ziliang, et al.
Published: (2026)