Imagen de Portada

Visualizing LLM Latent Space Geometry Through Dimensionality Reduction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ning, Alex, Rangaraju, Vainateya, Kuo, Yen-Ling
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Change-of-Basis Pruning via Rotational Invariance
por: Ning, Alex, et al.
Publicado: (2025)

Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning
por: Ning, Alex, et al.
Publicado: (2025)

Reformulation of RBM to Unify Linear and Nonlinear Dimensionality Reduction
por: You, Jiangsheng, et al.
Publicado: (2019)

Obfuscated Activations Bypass LLM Latent-Space Defenses
por: Bailey, Luke, et al.
Publicado: (2024)

Alternatives of Unsupervised Representations of Variables on the Latent Space
por: Glushkovsky, Alex
Publicado: (2024)

Mind the Gaps: Measuring Visual Artifacts in Dimensionality Reduction
por: Ros, Jaume, et al.
Publicado: (2025)

Improving Oral Cancer Outcomes Through Machine Learning and Dimensionality Reduction
por: Al-Batah, Mohammad Subhi, et al.
Publicado: (2025)

Improving the Generation of VAEs with High Dimensional Latent Spaces by the use of Hyperspherical Coordinates
por: Ascarate, Alejandro, et al.
Publicado: (2025)

mlx-vis: GPU-Accelerated Dimensionality Reduction and Visualization on Apple Silicon
por: Xiao, Han
Publicado: (2026)

UMATO: Bridging Local and Global Structures for Reliable Visual Analytics with Dimensionality Reduction
por: Jeon, Hyeon, et al.
Publicado: (2025)

Exploring the Impact of a Transformer's Latent Space Geometry on Downstream Task Performance
por: Marbut, Anna C., et al.
Publicado: (2024)

Supervised Quadratic Feature Analysis: Information Geometry Approach for Dimensionality Reduction
por: Herrera-Esposito, Daniel, et al.
Publicado: (2025)

A Large-Scale Sensitivity Analysis on Latent Embeddings and Dimensionality Reductions for Text Spatializations
por: Atzberger, Daniel, et al.
Publicado: (2024)

Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space
por: Mozafari-Nia, Mahsa, et al.
Publicado: (2024)

The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces
por: Bomatter, Philipp, et al.
Publicado: (2026)

Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture Translation
por: Armstrong, Marcus, et al.
Publicado: (2026)

Breaking Model Lock-in: Cost-Efficient Zero-Shot LLM Routing via a Universal Latent Space
por: Yan, Cheng, et al.
Publicado: (2026)

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
por: Yu, Shixing, et al.
Publicado: (2026)

Identifying Chemicals Through Dimensionality Reduction
por: Anand, Emile, et al.
Publicado: (2022)

Navigating High-Dimensional Backstage: A Guide for Exploring Literature for the Reliable Use of Dimensionality Reduction
por: Jeon, Hyeon, et al.
Publicado: (2025)

Understanding Latent Diffusability via Fisher Geometry
por: Gu, Jing, et al.
Publicado: (2026)

Diffusion Maps is not Dimensionality Reduction
por: Candanedo, Julio, et al.
Publicado: (2026)

Formation-Controlled Dimensionality Reduction
por: Jeong, Taeuk, et al.
Publicado: (2024)

Hessian Geometry of Latent Space in Generative Models
por: Lobashev, Alexander, et al.
Publicado: (2025)

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
por: Wang, Peihao, et al.
Publicado: (2026)

nSimplex Zen: A Novel Dimensionality Reduction for Euclidean and Hilbert Spaces
por: Connor, Richard, et al.
Publicado: (2023)

Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces
por: Geissler, Daniel, et al.
Publicado: (2024)

Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
por: Meherab, Md Muntaqim, et al.
Publicado: (2026)

Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning
por: Shan, Lianlei, et al.
Publicado: (2026)

Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein
por: Van Assel, Hugues, et al.
Publicado: (2024)

Latent SDEs on Homogeneous Spaces
por: Zeng, Sebastian, et al.
Publicado: (2023)

Latent Space Symmetry Discovery
por: Yang, Jianke, et al.
Publicado: (2023)

Median Consensus Embedding for Dimensionality Reduction
por: Tomo, Yui, et al.
Publicado: (2025)

Preserving Vector Space Properties in Dimensionality Reduction: A Relationship Preserving Loss Framework
por: Weinwurm, Eddi, et al.
Publicado: (2025)

All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models
por: Badrinath, Charumathi, et al.
Publicado: (2024)

LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuits
por: Kochar, Dimple Vijay, et al.
Publicado: (2024)

MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis
por: Huang, Zeyang, et al.
Publicado: (2026)

Unraveling the Localized Latents: Learning Stratified Manifold Structures in LLM Embedding Space with Sparse Mixture-of-Experts
por: Li, Xin, et al.
Publicado: (2025)

Latent Space Bayesian Optimization with Latent Data Augmentation for Enhanced Exploration
por: Boyar, Onur, et al.
Publicado: (2023)

Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
por: Kong, Deqian, et al.
Publicado: (2024)