:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Ziyue, Fan, Chenrui, Zhou, Tianyi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	https://arxiv.org/abs/2506.21551
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
por: Li, Ziyue, et al.
Publicado: (2025)

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
por: Li, Ziyue, et al.
Publicado: (2024)

R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts
por: Li, Zhongyang, et al.
Publicado: (2025)

Distributional Spectral Diagnostics for Localizing Grokking Transitions
por: Wang, Ziyue, et al.
Publicado: (2026)

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing
por: Li, Zhongyang, et al.
Publicado: (2025)

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
por: Li, Zhongyang, et al.
Publicado: (2025)

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
por: Fan, Chenrui, et al.
Publicado: (2025)

Schoenfeld's Anatomy of Mathematical Reasoning by Language Models
por: Li, Ming, et al.
Publicado: (2025)

Deep Grokking: Would Deep Neural Networks Generalize Better?
por: Fan, Simin, et al.
Publicado: (2024)

To Grok Grokking: Provable Grokking in Ridge Regression
por: Xu, Mingyue, et al.
Publicado: (2026)

NeuralGrok: Accelerate Grokking by Neural Gradient Transformation
por: Zhou, Xinyu, et al.
Publicado: (2025)

Memorization Dynamics of Fill-in-the-Middle Pretraining
por: von Arx, Tobias, et al.
Publicado: (2026)

Grokked Models are Better Unlearners
por: Liang, Yuanbang, et al.
Publicado: (2025)

Exploring Grokking: Experimental and Mechanistic Investigations
por: Qiye, Hu, et al.
Publicado: (2024)

Grokking Group Multiplication with Cosets
por: Stander, Dashiell, et al.
Publicado: (2023)

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions
por: Fan, Chenrui, et al.
Publicado: (2025)

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
por: Liang, Yijun, et al.
Publicado: (2025)

The Complexity Dynamics of Grokking
por: DeMoss, Branton, et al.
Publicado: (2024)

Measuring Sharpness in Grokking
por: Miller, Jack, et al.
Publicado: (2024)

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
por: Minegishi, Gouki, et al.
Publicado: (2023)

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
por: Li, Ming, et al.
Publicado: (2025)

Many-Objective Multi-Solution Transport
por: Li, Ziyue, et al.
Publicado: (2024)

Memorization Sinks: Isolating Memorization during LLM Training
por: Ghosal, Gaurav R., et al.
Publicado: (2025)

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
por: Wang, Xinyi, et al.
Publicado: (2024)

To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining
por: Singh, Karan, et al.
Publicado: (2026)

Topological Signatures of Grokking
por: Tang, Yifan, et al.
Publicado: (2026)

Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
por: Han, Ting, et al.
Publicado: (2025)

Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
por: Levi, Noam, et al.
Publicado: (2023)

The Pitfalls of Memorization: When Memorization Hurts Generalization
por: Bayat, Reza, et al.
Publicado: (2024)

ILDR: Geometric Early Detection of Grokking
por: Golwala, Shreel
Publicado: (2026)

Do Synthetic Trajectories Reflect Real Reward Hacking? A Systematic Study on Monitoring In-the-Wild Hacking in Code Generation
por: Li, Lichen, et al.
Publicado: (2026)

Variance-Adaptive Muon: Accelerating LLM Pretraining with NSR-Modulated and Variance-Scaled Momentum
por: Li, Jingru, et al.
Publicado: (2026)

Late-Stage Generalization Collapse in Grokking: Detecting anti-grokking with Weightwatcher
por: Prakash, Hari K, et al.
Publicado: (2026)

Grokking and Generalization Collapse: Insights from \texttt{HTSR} theory
por: Prakash, Hari K., et al.
Publicado: (2025)

TNT: Improving Chunkwise Training for Test-Time Memorization
por: Li, Zeman, et al.
Publicado: (2025)

Membership and Memorization in LLM Knowledge Distillation
por: Zhang, Ziqi, et al.
Publicado: (2025)

GrokAlign: Geometric Characterisation and Acceleration of Grokking
por: Walker, Thomas, et al.
Publicado: (2025)

Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
por: Zhang, Haochen, et al.
Publicado: (2025)

Titans: Learning to Memorize at Test Time
por: Behrouz, Ali, et al.
Publicado: (2024)

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
por: Hanqing, Liu, et al.
Publicado: (2026)