Copertina

Speech Tokenizer is Key to Consistent Representation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jung, Wonjin, Kang, Sungil, Cho, Dong-Yeon
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Multi-View Polymer Representations for the Open Polymer Prediction
di: Jung, Wonjin, et al.
Pubblicazione: (2025)

State Estimation Using Particle Filtering in Adaptive Machine Learning Methods: Integrating Q-Learning and NEAT Algorithms with Noisy Radar Measurements
di: Song, Wonjin, et al.
Pubblicazione: (2025)

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
di: Oh, YongKyung, et al.
Pubblicazione: (2025)

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
di: Oh, YongKyung, et al.
Pubblicazione: (2024)

DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis
di: Oh, YongKyung, et al.
Pubblicazione: (2024)

RepCodec: A Speech Representation Codec for Speech Tokenization
di: Huang, Zhichao, et al.
Pubblicazione: (2023)

Continuum Dropout for Neural Differential Equations
di: Lee, Jonghun, et al.
Pubblicazione: (2025)

Modeling Irregular Astronomical Time Series with Neural Stochastic Delay Differential Equations
di: Oh, YongKyung, et al.
Pubblicazione: (2025)

TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
di: Oh, YongKyung, et al.
Pubblicazione: (2025)

Subspace-based Approximate Hessian Method for Zeroth-Order Optimization
di: Kim, Dongyoon, et al.
Pubblicazione: (2025)

ConTEXTure: Consistent Multiview Images to Texture
di: Ahn, Jaehoon, et al.
Pubblicazione: (2024)

Spectral Analysis of Representational Similarity with Limited Neurons
di: Kang, Hyunmo, et al.
Pubblicazione: (2025)

Interdomain Attention: Beyond Token-Level Key-Value Memory
di: Kiyohara, Naoki, et al.
Pubblicazione: (2026)

Comprehensive Review of Neural Differential Equations for Time Series Analysis
di: Oh, YongKyung, et al.
Pubblicazione: (2025)

RL-BioAug: Label-Efficient Reinforcement Learning for Self-Supervised EEG Representation Learning
di: Lee, Cheol-Hui, et al.
Pubblicazione: (2026)

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
di: Song, Yakun, et al.
Pubblicazione: (2025)

Improving Self Consistency in LLMs through Probabilistic Tokenization
di: Sathe, Ashutosh, et al.
Pubblicazione: (2024)

Towards Improved Sentence Representations using Token Graphs
di: Mantri, Krishna Sri Ipsit, et al.
Pubblicazione: (2026)

Laplacian Heads Improve Transformers by Smoothing Token Representations
di: Zhang, Yuchong, et al.
Pubblicazione: (2026)

JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
di: Ioannides, Georgios, et al.
Pubblicazione: (2025)

Measuring Intrinsic Dimension of Token Embeddings
di: Kataiwa, Takuya, et al.
Pubblicazione: (2025)

AugWard: Augmentation-Aware Representation Learning for Accurate Graph Classification
di: Kim, Minjun, et al.
Pubblicazione: (2025)

Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
di: Halvagal, Manu Srinath, et al.
Pubblicazione: (2026)

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
di: Kim, Jaehyeon, et al.
Pubblicazione: (2024)

Feasibility Consistent Representation Learning for Safe Reinforcement Learning
di: Cen, Zhepeng, et al.
Pubblicazione: (2024)

Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
di: Kim, Sungnyun, et al.
Pubblicazione: (2025)

Efficient Training of Language Models with Compact and Consistent Next Token Distributions
di: Sathe, Ashutosh, et al.
Pubblicazione: (2024)

Autoregressive Speech Enhancement via Acoustic Tokens
di: Della Libera, Luca, et al.
Pubblicazione: (2025)

DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency
di: Chen, Yang, et al.
Pubblicazione: (2024)

WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records
di: Dong, Ruan, et al.
Pubblicazione: (2026)

Key Principles of Graph Machine Learning: Representation, Robustness, and Generalization
di: Abbahaddou, Yassine
Pubblicazione: (2026)

Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers
di: Chen, Jinsong, et al.
Pubblicazione: (2024)

Predictive Causal Inference via Spatio-Temporal Modeling and Penalized Empirical Likelihood
di: Lee, Byunghee, et al.
Pubblicazione: (2025)

PhysioME: A Robust Multimodal Self-Supervised Framework for Physiological Signals with Missing Modalities
di: Lee, Cheol-Hui, et al.
Pubblicazione: (2025)

TokenBlowUp: Resolving Representational Singularities in LLM Token Spaces via Monoidal Transformations
di: Zhao, Dongfang
Pubblicazione: (2025)

PAST: Phonetic-Acoustic Speech Tokenizer
di: Har-Tuv, Nadav, et al.
Pubblicazione: (2025)

Scaling Speech Tokenizers with Diffusion Autoencoders
di: Wang, Yuancheng, et al.
Pubblicazione: (2026)

STARS: Semantic Tokens with Augmented Representations for Recommendation at Scale
di: Chen, Han, et al.
Pubblicazione: (2025)

The Geometry of Tokens in Internal Representations of Large Language Models
di: Viswanathan, Karthik, et al.
Pubblicazione: (2025)

Behavior Structformer: Learning Players Representations with Structured Tokenization
di: Smirnov, Oleg, et al.
Pubblicazione: (2024)