Image de couverture de livre

Discrete Semantic States and Hamiltonian Dynamics in LLM Embedding Spaces

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Laine, Timo Aukusti
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Quantum LLM: Modeling Semantic Spaces with Quantum Principles
par: Laine, Timo Aukusti
Publié: (2025)

Semantic Wave Functions: Exploring Meaning in Large Language Models Through Quantum Formalism
par: Laine, Timo Aukusti
Publié: (2025)

Quantum LLMs Using Quantum Computing to Analyze and Process Semantic Information
par: Laine, Timo Aukusti
Publié: (2025)

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
par: Akkerman, Fabian, et autres
Publié: (2023)

ss-Mamba: Semantic-Spline Selective State-Space Model
par: Ye, Zuochen
Publié: (2025)

Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
par: Qu, Xingwei, et autres
Publié: (2025)

From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings
par: Biton, Dvir David, et autres
Publié: (2026)

Embedding Knowledge Graph in Function Spaces
par: Teyou, Louis Mozart Kamdem, et autres
Publié: (2024)

ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression
par: Liu, Guangda, et autres
Publié: (2024)

One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces
par: Sun, Yandong, et autres
Publié: (2025)

Scale-Consistent State-Space Dynamics via Fractal of Stationary Transformations
par: Yu, Geunhyeok, et autres
Publié: (2026)

Causal Abstraction Learning based on the Semantic Embedding Principle
par: D'Acunto, Gabriele, et autres
Publié: (2025)

Educational Cone Model in Embedding Vector Spaces
par: Ehara, Yo
Publié: (2025)

Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training
par: Milkert, Max, et autres
Publié: (2023)

SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces
par: Landers, Matthew, et autres
Publié: (2025)

Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation
par: Wang, Yiming, et autres
Publié: (2024)

GeoDynamics: A Geometric State-Space Neural Network for Understanding Brain Dynamics on Riemannian Manifolds
par: Dan, Tingting, et autres
Publié: (2026)

LLM Embeddings for Deep Learning on Tabular Data
par: Koloski, Boshko, et autres
Publié: (2025)

On the Dynamics of Observation and Semantics
par: Li, Xiu
Publié: (2026)

SemanticOpt: Towards LLM-Based Semantic Black-Box Optimization
par: Meindl, Jamison, et autres
Publié: (2025)

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
par: Schwalbe, Gesina, et autres
Publié: (2026)

Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space
par: van Spengler, Max, et autres
Publié: (2025)

Probing the Embedding Space of Transformers via Minimal Token Perturbations
par: Conti, Eddie, et autres
Publié: (2025)

Non-Stationarity in the Embedding Space of Time Series Foundation Models
par: Choi, Jinmyeong, et autres
Publié: (2026)

Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning
par: Zhu, Yuanyang, et autres
Publié: (2024)

Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces
par: Hoppe, Heiko, et autres
Publié: (2026)

Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids
par: Xiao, Qingyu, et autres
Publié: (2025)

Discrete State Diffusion Models: A Sample Complexity Perspective
par: Srikanth, Aadithya, et autres
Publié: (2025)

Analyzing and Improving the Training Dynamics of Diffusion Models
par: Karras, Tero, et autres
Publié: (2023)

Exploiting Temporal State Space Sharing for Video Semantic Segmentation
par: Hesham, Syed Ariff Syed, et autres
Publié: (2025)

Intrinsic-Energy Joint Embedding Predictive Architectures Induce Quasimetric Spaces
par: Kobanda, Anthony, et autres
Publié: (2026)

A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space
par: Wang, Zhangyu, et autres
Publié: (2024)

ES-Merging: Biological MLLM Merging via Embedding Space Signals
par: Lee, Wonbin, et autres
Publié: (2026)

Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring
par: Ayoughi, Melika, et autres
Publié: (2025)

Artificial Neural Nets and the Representation of Human Concepts
par: Freiesleben, Timo
Publié: (2023)

Q-function Decomposition with Intervention Semantics with Factored Action Spaces
par: Lee, Junkyu, et autres
Publié: (2025)

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
par: Zhang, Yuheng, et autres
Publié: (2026)

Learning Reconstructive Embeddings in Reproducing Kernel Hilbert Spaces via the Representer Theorem
par: Feito-Casares, Enrique, et autres
Publié: (2026)

Temporal Dynamic Embedding for Irregularly Sampled Time Series
par: Kim, Mincheol, et autres
Publié: (2025)

Stability and Discretization Error of State Space Model Neural Operators
par: Bendahi, Abderrahim, et autres
Publié: (2026)