:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Author:	Young, Robin
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	https://arxiv.org/abs/2603.03000
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Offline RLAIF: Piloting VLM Feedback for RL via SFO
by: Beck, Jacob
Published: (2025)

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
by: Lee, Harrison, et al.
Published: (2023)

Information-theoretic Distinctions Between Deception and Confusion
by: Young, Robin
Published: (2025)

Does Deep Active Learning Work in the Wild?
by: Ren, Simiao, et al.
Published: (2023)

Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
by: Zhao, Yike, et al.
Published: (2026)

Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control
by: Lawrence, Nathan P., et al.
Published: (2025)

Why Do Some Inputs Break Low-Bit LLM Quantization?
by: Chang, Ting-Yun, et al.
Published: (2025)

What Is the Alignment Tax?
by: Young, Robin
Published: (2026)

Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
by: Zhu, Yifan, et al.
Published: (2026)

Does Your Wildfire Prediction Model Actually Work, or Just Score Well?
by: Xu, Yangshuang, et al.
Published: (2026)

Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models
by: Tian, Bowei, et al.
Published: (2025)

Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
by: Sernau, Luke
Published: (2024)

Feature-Enhanced Machine Learning for All-Cause Mortality Prediction in Healthcare Data
by: Lee, HyeYoung, et al.
Published: (2025)

Why Adam Works Better with $β_1 = β_2$: The Missing Gradient Scale Invariance Principle
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
by: Öncel, Fırat, et al.
Published: (2024)

One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache
by: Lu, Liming, et al.
Published: (2026)

Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models
by: Juzek, Tom S., et al.
Published: (2024)

Why Does Stochastic Gradient Descent Slow Down in Low-Precision Training?
by: Yun, Vincent-Daniel
Published: (2025)

Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis
by: Wang, Qunzhong, et al.
Published: (2024)

One Size Does Not Fit All: A Distribution-Aware Sparsification for More Precise Model Merging
by: Luo, Yingfeng, et al.
Published: (2025)

Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation
by: McLaren, Lorcan, et al.
Published: (2026)

Learning Through Noise: Why Subliminal Learning Works and When It Fails
by: Brockers, Vincent C., et al.
Published: (2026)

Does This Gradient Spark Joy?
by: Osband, Ian
Published: (2026)

Why Do Language Model Agents Whistleblow?
by: Agrawal, Kushal, et al.
Published: (2025)

Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models
by: Son, Hyegang, et al.
Published: (2024)

DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal models
by: Blöbaum, Patrick, et al.
Published: (2022)

AllMatch: Exploiting All Unlabeled Data for Semi-Supervised Learning
by: Wu, Zhiyu, et al.
Published: (2024)

The Depth Delusion: Why Transformers Should Be Wider, Not Deeper
by: Fahim, Md Muhtasim Munif, et al.
Published: (2026)

Why pre-training is beneficial for downstream classification tasks?
by: Jiang, Xin, et al.
Published: (2024)

Why and How Auxiliary Tasks Improve JEPA Representations
by: Yu, Jiacan, et al.
Published: (2025)

Why Gradients Rapidly Increase Near the End of Training
by: Defazio, Aaron
Published: (2025)

Why Transformers Need Adam: A Hessian Perspective
by: Zhang, Yushun, et al.
Published: (2024)

WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
by: Drouin, Alexandre, et al.
Published: (2024)

Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
by: Lowy, Andrew, et al.
Published: (2024)

Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
by: Bergsma, Shane, et al.
Published: (2025)

Context is All You Need
by: Delanois, Jean Erik, et al.
Published: (2026)

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
by: Yu, Yunrui, et al.
Published: (2026)

Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It
by: Tai, Wenxin, et al.
Published: (2026)

Why Inference in Large Models Becomes Decomposable After Training
by: Jin, Jidong
Published: (2026)

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
by: Armandpour, Mohammadreza, et al.
Published: (2026)