Image de couverture de livre

Inverse Depth Scaling From Most Layers Being Similar

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Yizhou, Kangaslahti, Sara, Liu, Ziming, Gore, Jeff
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Dynamical Systems
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Superposition Yields Robust Neural Scaling
par: Liu, Yizhou, et autres
Publié: (2025)

Universal One-third Time Scaling in Learning Peaked Distributions
par: Liu, Yizhou, et autres
Publié: (2026)

Neural Thermodynamic Laws for Large Language Model Training
par: Liu, Ziming, et autres
Publié: (2025)

Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
par: Wang, Shida, et autres
Publié: (2023)

A Resource Model For Neural Scaling Law
par: Song, Jinyeop, et autres
Publié: (2024)

Language models as master equation solvers
par: Liu, Chuanbo, et autres
Publié: (2023)

Complex fractal trainability boundary can arise from trivial non-convexity
par: Liu, Yizhou
Publié: (2024)

Manifold Trajectories in Next-Token Prediction: From Replicator Dynamics to Softmax Equilibrium
par: Lee-Jenkins, Christopher R.
Publié: (2025)

Physics of Skill Learning
par: Liu, Ziming, et autres
Publié: (2025)

Second Order Ensemble Langevin Method for Sampling and Inverse Problems
par: Liu, Ziming, et autres
Publié: (2022)

Horizon-Constrained Rashomon Sets for Chaotic Forecasting
par: Kale, Gauri, et autres
Publié: (2026)

True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics
par: Hemmer, Christoph Jürgen, et autres
Publié: (2025)

Out-of-Domain Generalization in Dynamical Systems Reconstruction
par: Göring, Niclas, et autres
Publié: (2024)

Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction
par: Hemmer, Christoph Jürgen, et autres
Publié: (2024)

A Mathematical Conflict Framework for Contextual Data Modulation
par: Kartal, Hakan Emre
Publié: (2026)

Dynamical Systems Theory Behind a Hierarchical Reasoning Model
par: Es'kin, Vasiliy A., et autres
Publié: (2026)

Large-Step Training Dynamics of a Two-Factor Linear Transformer Model
par: Balasubramanian, Krishnakumar
Publié: (2026)

Late Fusion Neural Operators for Extrapolation Across Parameter Space in Partial Differential Equations
par: van Tegelen, Eva, et autres
Publié: (2026)

Position: Why a Dynamical Systems Perspective is Needed to Advance Time Series Modeling
par: Durstewitz, Daniel, et autres
Publié: (2026)

A Minimal Bifurcation Model of Load Imbalance in a Softmax Mixture-of-Experts Router
par: Kiselev, O. M.
Publié: (2026)

A-PINN: Auxiliary Physics-informed Neural Networks for Structural Vibration Analysis in Continuous Euler-Bernoulli Beam
par: Saini, Shivani, et autres
Publié: (2025)

Identifying Equivalent Training Dynamics
par: Redman, William T., et autres
Publié: (2023)

Detecting Invariant Manifolds in ReLU-Based RNNs
par: Eisenmann, Lukas, et autres
Publié: (2025)

Decomposing heterogeneous dynamical systems with graph neural networks
par: Allier, Cédric, et autres
Publié: (2024)

Improved deep learning of chaotic dynamical systems with multistep penalty losses
par: Chakraborty, Dibyajyoti, et autres
Publié: (2024)

A Hybrid Approach of Transfer Learning and Physics-Informed Modeling: Improving Dissolved Oxygen Concentration Prediction in an Industrial Wastewater Treatment Plant
par: Koksal, Ece S., et autres
Publié: (2024)

On the Limitations of Fractal Dimension as a Measure of Generalization
par: Tan, Charlie B., et autres
Publié: (2024)

The Recurrent Sticky Hierarchical Dirichlet Process Hidden Markov Model
par: Słupiński, Mikołaj, et autres
Publié: (2024)

Bayesian Inference in Recurrent Explicit Duration Switching Linear Dynamical Systems
par: Słupiński, Mikołaj, et autres
Publié: (2024)

On the dimension of pullback attractors in recurrent neural networks
par: Fadera, Muhammed
Publié: (2025)

Confabulation dynamics in a reservoir computer: Filling in the gaps with untrained attractors
par: O'Hagan, Jack, et autres
Publié: (2025)

Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks
par: Gao, Mars Liyao, et autres
Publié: (2025)

Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Models
par: Hoover, Benjamin, et autres
Publié: (2023)

Improving physics-informed neural network extrapolation via transfer learning and adaptive activation functions
par: Papastathopoulos-Katsaros, Athanasios, et autres
Publié: (2025)

Hybrid Energy-Based Models for Physical AI: Provably Stable Identification of Port-Hamiltonian Dynamics
par: Betteti, Simone, et autres
Publié: (2026)

Kernel Dynamics under Path Entropy Maximization
par: Das, Jnaneshwar
Publié: (2026)

How to Tame Your LLM: Semantic Collapse in Continuous Systems
par: Wyss, C. M.
Publié: (2025)

A Hybrid Adaptive Velocity Aided Navigation Filter with Application to INS/DVL Fusion
par: Or, Barak, et autres
Publié: (2022)

Learning Chaotic Systems and Long-Term Predictions with Neural Jump ODEs
par: Krach, Florian, et autres
Publié: (2024)

FOCUS: First Order Concentrated Updating Scheme
par: Liu, Yizhou, et autres
Publié: (2025)