Image de couverture de livre

Harmonic Token Projection (HTP): A Vocabulary-Free, Training-Free, Deterministic, and Reversible Embedding Methodology

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Schmitz, Tcharlies
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Modular Linear Tokenization (MLT)
par: Schmitz, Tcharlies
Publié: (2025)

Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
par: Işık, İlker, et autres
Publié: (2024)

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit
par: Goddard, Charles, et autres
Publié: (2025)

Attention with Trained Embeddings Provably Selects Important Tokens
par: Wu, Diyuan, et autres
Publié: (2025)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
par: Deiseroth, Björn, et autres
Publié: (2024)

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling
par: Huang, Hongzhi, et autres
Publié: (2025)

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
par: Yang, Wang, et autres
Publié: (2026)

Memory Tokens: Large Language Models Can Generate Reversible Sentence Embeddings
par: Sastre, Ignacio, et autres
Publié: (2025)

Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB
par: Ren, Xingyu, et autres
Publié: (2025)

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
par: Li, Ziyue, et autres
Publié: (2024)

Detecting Token-Level Hallucinations Using Variance Signals: A Reference-Free Approach
par: Kumar, Keshav
Publié: (2025)

Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
par: Yakushev, George, et autres
Publié: (2025)

Training-Free Dynamic Upcycling of Expert Language Models
par: Fanì, Eros, et autres
Publié: (2026)

Token Distillation: Attention-aware Input Embeddings For New Tokens
par: Dobler, Konstantin, et autres
Publié: (2025)

NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
par: Si, Chongjie, et autres
Publié: (2025)

X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation
par: Sreenivas, Sharath Turuvekere, et autres
Publié: (2026)

Measuring Intrinsic Dimension of Token Embeddings
par: Kataiwa, Takuya, et autres
Publié: (2025)

VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
par: Amballa, Avinash, et autres
Publié: (2025)

Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP
par: Remy, François, et autres
Publié: (2024)

Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
par: Chen, Daiwei, et autres
Publié: (2026)

SeMe: Training-Free Language Model Merging via Semantic Alignment
par: Gu, Jian, et autres
Publié: (2025)

LEWIS (LayEr WIse Sparsity) -- A Training Free Guided Model Merging Approach
par: Chopra, Hetarth, et autres
Publié: (2025)

Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models
par: Roger, Alexis, et autres
Publié: (2025)

Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation
par: Li, Zongxia, et autres
Publié: (2025)

First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models
par: Ma, Chi, et autres
Publié: (2024)

LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
par: Lee, Unggi, et autres
Publié: (2026)

Training-Free Spectral Fingerprints of Voice Processing in Transformers
par: Noël, Valentin
Publié: (2025)

Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size
par: Hayou, Soufiane, et autres
Publié: (2025)

Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch
par: Zhang, Ziyang, et autres
Publié: (2025)

Reasoning Bias of Next Token Prediction Training
par: Lin, Pengxiao, et autres
Publié: (2025)

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
par: Feucht, Sheridan, et autres
Publié: (2024)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
par: Katz, Shahar, et autres
Publié: (2024)

Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models
par: Lou, Xingzhou, et autres
Publié: (2024)

When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars
par: Higuchi, Rei, et autres
Publié: (2025)

ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment
par: Obbad, Elyas, et autres
Publié: (2024)

Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern
par: Tang, Hongyin, et autres
Publié: (2024)

Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings
par: Ding, Xueying, et autres
Publié: (2025)

FoNE: Precise Single-Token Number Embeddings via Fourier Features
par: Zhou, Tianyi, et autres
Publié: (2025)

Bifocal Attention: Harmonizing Geometric and Spectral Positional Embeddings for Algorithmic Generalization
par: Awadhiya, Kanishk
Publié: (2026)

Is Free Self-Alignment Possible?
par: Adila, Dyah, et autres
Publié: (2024)