Token-Level Uncertainty

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-14

9 new papers

A weekly snapshot of new work published in Token-Level Uncertainty.

Period ending 2026-09-07

14 new papers

A weekly snapshot of new work published in Token-Level Uncertainty.

Inside this field

Focused directions

Focused topic

Token-Level Uncertainty

Within Token-Level Uncertainty

170 papersExplore

Focused topic

Tokenizer

Within Token-Level Uncertainty

105 papersExplore

Focused topic

Object Tokens

Within Token-Level Uncertainty

37 papersExplore

308 papers

Latest in Token-Level Uncertainty

Open your feed →

On the role of the tokenizer in ECG transformer models
Sep 14, 2026Jiawei Li, Fabio Bonassi, Johan Sundström +2Tokenizer
IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing
Sep 11, 2026Pruthwik Mishra, Rudra Trivedi, Avi Patel +2Indic Languages Token-Level Uncertainty
Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy Loss
Sep 10, 2026Zhijian Li, Stefan Larson, Kevin LeachLarge Language Model Memory Token-Level Uncertainty
Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format
Sep 9, 2026Touchapon Kraisingkorn, Krittin Pachtrachai, Wachiravit ModecruaRationales Elicitation
StreamAlign: Streaming Text-Aligned Speech Tokenization
Sep 9, 2026Kang-wook Kim, Jinyoung Park, Jinsoo Kim +3Automatic Speech Recognition Tokenizer
BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models
Sep 9, 2026Shivam Singh, Aditya Yadavalli, Catherine Arnett +1Automatic Speech Recognition Model Whisper-Large-V3
Studying Image Tokenizers as Visual Languages in Unified Multimodal Models
Sep 8, 2026Siting Li, Zhengyang Wang, Simon Shaolei Du +2Multimodal Learning Tokenizer
TV-Regulated OPD: Direction Matters in On-Policy Distillation
Sep 8, 2026Han Xiao, Yifan Niu, Dongyi Liu +2On-Policy Distillation Token-Level Uncertainty
Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?
Sep 8, 2026Bangshuo Zhu, Wei Song, Yuxin Cao +4Video Large Language Models Adversarial Attack Strategies
Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Serving-Time Weight Compression
Sep 7, 2026Dachi KurtskhaliaLarge Language Model Quantization Quantization Effects
Compressing Streaming Neural Audio Encoders via Latent-Space Distillation
Sep 3, 2026Prasanth Yadla, Mohammad Samragh, Dongseong Hwang +7Neural Audio Codecs Tokenizer
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
Sep 1, 2026Matteo He, William F. Shen, Xinchi Qiu +1Readout Logit Lens
Subword Segmental BabyLMs: Learning to Tokenise for Sample-Efficient Pretraining
Sep 1, 2026Francois MeyerSubword Tokenization Large Language Model Post-Training
PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian
Sep 1, 2026Mohammad Hossein Shalchian, Mostafa Amiri, Amir Mahdi SadeghzadehAnonymization Named-Entity Recognition
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
Sep 1, 2026Shengfang Zhai, Leo Marchyok, Yuling Shi +4Membership Inference Diffusion Language Models
FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation
Sep 1, 2026Kewei Li, Rongying Zhang, Xueli Wang +6Global Average Pooling Frequency Domain
Measuring Optimal Transport in Transformer Depth
Sep 1, 2026Alexandre QuemyOptimal Transport Object Tokens
Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought Compression
Aug 31, 2026Tianyi Zhao, Yinhan He, Wendy Zheng +1Chain-Of-Thought Reasoning Chain
Beat-Synchronous Tokenization for ECG Transformers
Aug 31, 2026Ahmed Sameh, Nolan Wilson, Max Enderlein +1Electrocardiogram Tokenizer
Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Family Representation Steering
Aug 31, 2026Jin Gan, Xin Li, Jun LuoInference-Time Defense Large Language
Manacá-1B: An Open, Reproducible Brazilian-Portuguese Language Model and a Tokenizer-Aware, Paired Evaluation
Aug 31, 2026Bruno Leonardo Santos Menezes, Carlos Leonardo Souza Cardoso, Fabio Andre Machado PortoPortuguese Protein Language Model
Game-Agnostic Value Functions through Automatic JSON Feature Extraction
Aug 30, 2026Dien Nguyen, Diego Perez-LiebanaValue Functions Value
Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprinting
Aug 30, 2026Bo ChenToken-Level Uncertainty Lineages
INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction
Aug 30, 2026Shahar Oded, Yuval ShaharClinical Prediction Mimic-Iv Datasets
Token-Oriented Semantic Communication with Pretrained Vision Transformers
Aug 26, 2026Jiwoong Im, Minwoo Kim, Jaeho Lee +2Token Compression Self-Supervised Vision Transformers
PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization
Aug 25, 2026Yunxiao Luo, Siyuan Wang, Ben Chen +2Residual Quantization Tokenizer
TokEval: A Tokenizer Evaluation Suite
Aug 18, 2026Clara MeisterTokenizer Protein Language Model
Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services
Aug 13, 2026Ahmet Bugra Gundogan, Yigit Turkmen, Melih BastopcuLLM Reasoning Methods Token-Level Uncertainty
vToken: Token-Level Virtualization for Reclaimable KV Caches
Aug 13, 2026Yuanhang Gao, Xiangrui Yang, Yuanfeng Chen +4Key-Value Cache Graphics Processing Unit Memory
MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
Aug 12, 2026Ming Zhang, Kaisen Yang, Shu Yu +6Recurrent Model Efficient Long-Context Inference
Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization
Aug 12, 2026Peijie Chen, Zhuanling Zha, Zhipeng Nie +8Autoregressive Text-To-Speech Text-To-Speech
REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation
Aug 12, 2026Yang Sun, Lichao Ma, Houyuan Qin +5On-Policy Distillation On-Policy
Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents
Aug 12, 2026Dylan Bouchard, Mohit Singh ChauhanLarge Language Model Uncertainty Large Language Model Agents
UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
Aug 11, 2026Dvir Samuel, Guy Bar-Shalom, Fabrizio Frasca +4Large Language Model Hallucination Hallucination Detection
Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?
Aug 11, 2026Qingjie Zhang, Xingzhang Ren, Zixuan Chen +6Token-Level Uncertainty Corpus
Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics
Aug 11, 2026Qingjie Zhang, Ziqi Tang, Jie Zhang +7Corpus Byte-Pair Encoding
MedUP: Awakening Unified Understanding and Perception in Medical Vision-Language Models
Aug 11, 2026Yuan Wang, Hualiang Wang, Yixin Chen +6Medical Vision-Language Models Perception
Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases
Aug 11, 2026Davood Wadi, Mohsen Ghodrat, Matthew PhilpLarge Language Model Bias Large Language Model Evaluation
SR-OPSD: Self-Referenced On-Policy Self-Distillation
Aug 10, 2026Zhuo Sun, Entong Li, Yanlong Zhao +7Unsupervised On-Policy Self-Distillation Self-Teacher
Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization
Aug 10, 2026Wenxiao Zhao, Shu Wang, Ying Nian WuTopic-Disjoint Direct Preference Optimization Data Token-Level Uncertainty
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
Aug 10, 2026Kristian Schwethelm, Daniel Rueckert, Georgios KaissisBatch Size Protein Language Model
Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations
Aug 10, 2026Weijie Liang, Yuanfeng Song, Xing Chen +3Repository-Level Code Understanding Coding Agents
Tokenizer Generator Coupling in Medical Image Generation
Aug 7, 2026Liam ChalcroftMedical Image Generation Tokenizer
Reading Copom's Tone: A Weighted LLM Framework for Hawkish-Dovish Sentiment, Forward Guidance, and Uncertainty
Aug 7, 2026Gabriel de Macedo SantosFinancial Sentiment Analysis Sentiment Analysis
Every Cache Entry Earns Its Place: Global Allocation of Resolution and Coverage for KV Cache Compression
Aug 7, 2026Haolin Tian, Yuzhe Liu, Tonghan WangKey-Value Cache Compression Graphics Processing Unit Memory
FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding
Aug 7, 2026Quanquan Li, Hongbo Zhang, Yihe Chi +9LLM Reasoning Methods Token-Level Uncertainty
Training-Free Token-Level Steering for LLM Personalized Co-Writing
Aug 6, 2026Wenhao Mao, Chengbin Hou, Weixiao Wang +4Large Language Model Personalization Ai-Assisted Writing
KVAE: Family of Tokenizers for Multimodal Generative Models
Aug 6, 2026Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov +11Discrete Image Tokenizers Variational Autoencoder Latent
Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation
Aug 4, 2026Junhao Chen, Mingjin Chen, Jingjia Mao +12Generative Music Models Tokenizer
TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning
Aug 4, 2026Wonpyo Park, Seung-won HwangKey-Value Cache Compression Key-Value Cache Eviction
CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning
Aug 4, 2026Ziqi Jia, Yalu Ouyang, Bo Pang +5LLM Reasoning Methods Curriculum Reinforcement Learning
Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs
Aug 3, 2026Iaroslav Chelombitko, Ekaterina Chelombitko, Mika HämäläinenCultural Alignment Cross-Lingual Consistency
Token-Native Storage: Read and Write in your Agent's Language
Aug 3, 2026Kumar ShivenduByte-Pair Encoding Tokenizer
Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Actions
Aug 3, 2026Jinghan Xu, Longze Fan, Zeyuan Wang +2Authorization Token-Level Uncertainty
Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models
Aug 2, 2026Leyan Xue, Feng Xiong, Mingjun Ma +1On-Policy Distillation Training-Inference Mismatch
3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering
Aug 2, 2026Changwoo Baek, Kyeongbo KongToken Compression Redundancy
Morphology Aware Reversible Semantic Tokenization and Hierarchical Word Composition for Tamil Language Models
Aug 2, 2026Anand MuruganSubword Tokenization Tokenizer
Writing-System-Level Tokenizer Adaptation for Byte-Level BPE
Aug 1, 2026Bohdan DidenkoByte-Pair Encoding Tokenizer
Agentic Graph Token Reasoning
Aug 1, 2026Zhuoyi Peng, Yi YangNeural Tokens Agentic Reasoning
TrAC: Trace-Conditioned Answer Consistency for Efficient Uncertainty Quantification in LLMs
Aug 1, 2026Dahai Yu, Lin Jiang, Rongchao Xu +1Large Language Model Uncertainty LLM Reasoning Methods

Sep 14, 2026 · cs.LGJ/K move · Enter open · S save

On the role of the tokenizer in ECG transformer models

Jiawei Li, Fabio Bonassi, Johan Sundström, Thomas B. Schön+1

Tokenization determines both the physiological content presented to an ECG Transformer and the sequence over which attention operates. We compare eight tokenization strategies across Transformer, Informer, Reformer, and FEDformer on the nine-label CPSC2018 classification task. The input projection and principal backbone capacity are controlled to isolate the effect of token construction. Median-beat and HeartLang tokenization achieve mean macro-AUCs of 0.893 and 0.889 across the four backbones, compared with 0.822 and 0.824 for point-wise and patch-wise tokenization. Pooling the two physiology-aware representations yields an 8.2% relative improvement in macro-AUC. They also reduce mean sequence length from 1,250 to 158 tokens and mean peak training memory from 5.21 to 0.27 GB. The results show that aligning tokens with ECG morphology can improve both predictive performance and memory efficiency without increasing backbone capacity. The source code is available on https://github.com/LeeJarvis996/ecg_tokenizer.

Tokenizer

Open paper Ask about it PDF