Guardado en:
| Autores principales: | Gurnee, Wes, Ameisen, Emmanuel, Kauvar, Isaac, Tarng, Julius, Pearce, Adam, Olah, Chris, Batson, Joshua |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2601.04480 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
Emotion Concepts and their Function in a Large Language Model
por: Sofroniew, Nicholas, et al.
Publicado: (2026)
por: Sofroniew, Nicholas, et al.
Publicado: (2026)
Language Models Represent Space and Time
por: Gurnee, Wes, et al.
Publicado: (2023)
por: Gurnee, Wes, et al.
Publicado: (2023)
Not All Language Model Features Are One-Dimensionally Linear
por: Engels, Joshua, et al.
Publicado: (2024)
por: Engels, Joshua, et al.
Publicado: (2024)
Policy-shaped prediction: avoiding distractions in model-based reinforcement learning
por: Hutson, Miles, et al.
Publicado: (2024)
por: Hutson, Miles, et al.
Publicado: (2024)
The Remarkable Robustness of LLMs: Stages of Inference?
por: Lad, Vedang, et al.
Publicado: (2024)
por: Lad, Vedang, et al.
Publicado: (2024)
Refusal in Language Models Is Mediated by a Single Direction
por: Arditi, Andy, et al.
Publicado: (2024)
por: Arditi, Andy, et al.
Publicado: (2024)
Confidence Regulation Neurons in Language Models
por: Stolfo, Alessandro, et al.
Publicado: (2024)
por: Stolfo, Alessandro, et al.
Publicado: (2024)
Universal Neurons in GPT2 Language Models
por: Gurnee, Wes, et al.
Publicado: (2024)
por: Gurnee, Wes, et al.
Publicado: (2024)
Mechanisms of Introspective Awareness
por: Macar, Uzay, et al.
Publicado: (2026)
por: Macar, Uzay, et al.
Publicado: (2026)
When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis
por: Li, Xiang, et al.
Publicado: (2025)
por: Li, Xiang, et al.
Publicado: (2025)
The Geometry of Self-Verification in a Task-Specific Reasoning Model
por: Lee, Andrew, et al.
Publicado: (2025)
por: Lee, Andrew, et al.
Publicado: (2025)
Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders
por: Rhodes, Jake S., et al.
Publicado: (2025)
por: Rhodes, Jake S., et al.
Publicado: (2025)
GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds
por: Chen, Aoran, et al.
Publicado: (2025)
por: Chen, Aoran, et al.
Publicado: (2025)
Auditing language models for hidden objectives
por: Marks, Samuel, et al.
Publicado: (2025)
por: Marks, Samuel, et al.
Publicado: (2025)
Exploring the Manifold of Neural Networks Using Diffusion Geometry
por: Abel, Elliott, et al.
Publicado: (2024)
por: Abel, Elliott, et al.
Publicado: (2024)
Combatting Gerrymandering with Ranked Choice Voting: An Experimental Analysis of Multi-member Districts in the United States
por: Garg, Nikhil, et al.
Publicado: (2021)
por: Garg, Nikhil, et al.
Publicado: (2021)
Staying on the Manifold: Geometry-Aware Noise Injection
por: Jacobsen, Albert Kjøller, et al.
Publicado: (2025)
por: Jacobsen, Albert Kjøller, et al.
Publicado: (2025)
Manifold Diffusion Fields
por: Elhag, Ahmed A., et al.
Publicado: (2023)
por: Elhag, Ahmed A., et al.
Publicado: (2023)
Latent Planning Emerges with Scale
por: Hanna, Michael, et al.
Publicado: (2026)
por: Hanna, Michael, et al.
Publicado: (2026)
Geometry-Aware Uncertainty Quantification via Conformal Prediction on Manifolds
por: Shahbazi, Marzieh Amiri, et al.
Publicado: (2026)
por: Shahbazi, Marzieh Amiri, et al.
Publicado: (2026)
Learning to Normalize on the SPD Manifold under Bures-Wasserstein Geometry
por: Wang, Rui, et al.
Publicado: (2025)
por: Wang, Rui, et al.
Publicado: (2025)
Random Forest-Supervised Manifold Alignment
por: Rhodes, Jake S., et al.
Publicado: (2024)
por: Rhodes, Jake S., et al.
Publicado: (2024)
The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
por: Musat, Tiberiu
Publicado: (2025)
por: Musat, Tiberiu
Publicado: (2025)
When Can Transformers Count to n?
por: Yehudai, Gilad, et al.
Publicado: (2024)
por: Yehudai, Gilad, et al.
Publicado: (2024)
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
por: Wurgaft, Daniel, et al.
Publicado: (2026)
por: Wurgaft, Daniel, et al.
Publicado: (2026)
Geometry-Preserving Neural Architectures on Manifolds with Boundary
por: Elamvazhuthi, Karthik, et al.
Publicado: (2026)
por: Elamvazhuthi, Karthik, et al.
Publicado: (2026)
Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
por: Farghly, Tyler, et al.
Publicado: (2025)
por: Farghly, Tyler, et al.
Publicado: (2025)
Large Language-Geometry Model: When LLM meets Equivariance
por: Li, Zongzhao, et al.
Publicado: (2025)
por: Li, Zongzhao, et al.
Publicado: (2025)
Graph Integration for Diffusion-Based Manifold Alignment
por: Rhodes, Jake S., et al.
Publicado: (2024)
por: Rhodes, Jake S., et al.
Publicado: (2024)
Vector Symbolic Algebras for the Abstraction and Reasoning Corpus
por: Joffe, Isaac, et al.
Publicado: (2025)
por: Joffe, Isaac, et al.
Publicado: (2025)
When can transformers reason with abstract symbols?
por: Boix-Adsera, Enric, et al.
Publicado: (2023)
por: Boix-Adsera, Enric, et al.
Publicado: (2023)
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
por: Diepeveen, Willem, et al.
Publicado: (2024)
por: Diepeveen, Willem, et al.
Publicado: (2024)
Learning When to Switch: Adaptive Policy Selection via Reinforcement Learning
por: Tava, Chris
Publicado: (2025)
por: Tava, Chris
Publicado: (2025)
Discovering Data Manifold Geometry via Non-Contracting Flows
por: Vigouroux, David, et al.
Publicado: (2026)
por: Vigouroux, David, et al.
Publicado: (2026)
Manifold-Matching Autoencoders
por: Cheret, Laurent, et al.
Publicado: (2026)
por: Cheret, Laurent, et al.
Publicado: (2026)
Understanding When Poisson Log-Normal Models Outperform Penalized Poisson Regression for Microbiome Count Data
por: Agyapong, Daniel, et al.
Publicado: (2026)
por: Agyapong, Daniel, et al.
Publicado: (2026)
Divisive Decisions: Improving Salience-Based Training for Generalization in Binary Classification Tasks
por: Piland, Jacob, et al.
Publicado: (2025)
por: Piland, Jacob, et al.
Publicado: (2025)
Manifold Matching using Shortest-Path Distance and Joint Neighborhood Selection
por: Shen, Cencheng, et al.
Publicado: (2014)
por: Shen, Cencheng, et al.
Publicado: (2014)
Diffusion Processes on Implicit Manifolds
por: Kawasaki-Borruat, Victor, et al.
Publicado: (2026)
por: Kawasaki-Borruat, Victor, et al.
Publicado: (2026)
Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
por: Sun, Xingzhi, et al.
Publicado: (2024)
por: Sun, Xingzhi, et al.
Publicado: (2024)
Ejemplares similares
-
Emotion Concepts and their Function in a Large Language Model
por: Sofroniew, Nicholas, et al.
Publicado: (2026) -
Language Models Represent Space and Time
por: Gurnee, Wes, et al.
Publicado: (2023) -
Not All Language Model Features Are One-Dimensionally Linear
por: Engels, Joshua, et al.
Publicado: (2024) -
Policy-shaped prediction: avoiding distractions in model-based reinforcement learning
por: Hutson, Miles, et al.
Publicado: (2024) -
The Remarkable Robustness of LLMs: Stages of Inference?
por: Lad, Vedang, et al.
Publicado: (2024)