ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “soft tokens”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CLcs.AIcs.LGEmpiricalRecentOct 30, 2026

In-Model Context Compression with Agentic Soft Tokens for Long-Horizon LLM Agents

Xuning He, Kai Fan, Runyu Zhang, Binghuan Wang +3 more

This paper introduces a training-free compression method for long-horizon LLM agents using soft tokens.

View →
cs.AIRecentMay 27, 2026

Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection

Zhixing Zuo, Huilin He, Jiasheng Wu, Dawei Cheng

The paper proposes the LLM-GNN Soft Prompt Framework (LGSPF) to enhance fraud detection by directly integrating graph structure and semantic information into LLMs, achieving state-of-the-art performan…

View →
cs.CEq-fin.CPRecentMay 31, 2026

Tokenized but Illiquid? Evidence from Real-World Asset Markets

Rischan Mafrur

The paper investigates whether tokenizing real-world assets actually improves liquidity, finding that liquidity is highly heterogeneous across asset types and is not reliably predicted by the outstand…

View →
cs.AIcs.CLRecentMay 28, 2026

Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI Systems

Lorenz Kutschka, Bernhard Geiger

This study benchmarks token-optimized formats (TOON and TRON) against JSON in end-to-end agentic AI systems, finding that TRON significantly reduces token overhead with minimal performance degradation…

View →
cs.CLcs.AIRecentJun 1, 2026

AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training

Liu Qing, Ou Wu, Yi Du

AlphaToken is a novel response token valuation framework that improves LLM post-training by decoupling token selection into task-specific adaptation and stability preservation, leading to better perfo…

View →
cs.CRcs.AIcs.CCRecentJun 3, 2026

Token Rankings are Unforgeable Language Model Signatures

Matthew Finlayson, Andreas Grivas, Xiang Ren, Swabha Swayamdipta

The paper demonstrates that token rankings provide a unique, unforgeable signature for language models, and proposes an API restriction that allows for signature presentation without leaking model par…

View →
cs.LGcs.AIcs.SEEmpiricalRecentSep 28, 2026

TokenCast: Forecasting Token Consumption During LLM Agent Execution

Chaoqian Ouyang, Ling Yue, Libin Zheng, Huanghui Guo +6 more

This paper proposes TokenCast, a method to predict and control the token consumption of large language model agents.

View →
cs.CRcs.AIcs.LGMar 24, 2026

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

Wenyu Chen, Xiangtao Meng, Chuanchao Zang, Li Wang +5 more

The paper proposes TriageFuzz, a token-aware fuzzing framework that significantly reduces the number of queries needed to jailbreak LLMs while maintaining high attack success rates.

View →
cs.CREmpiricalRecentJul 17, 2026

Gasp: A DeFi Application Specic Rollup as a Consolidation Layer for All Assets

Stanislav Vozarik, Mateusz Nowakowski, Shoeb Siddiqui, Elliot Hill +2 more

Gasp is a decentralized exchange using optimistic rollup technology for gas-free, native cross-chain swaps with security guarantees and liquidity incentives.

View →
cs.IRcs.AIRecentMay 29, 2026

LLMs Need Encoders for Semantic IDs Too

Xiangyi Chen, Zelun Wang, Xinyi Li, Yi-Ping Hsu +2 more

The paper proposes PrefixMem, a dedicated encoder for Semantic IDs (SIDs), demonstrating that structured, prefix-conditioned representations significantly improve the accuracy and recall of generative…

View →
cs.CLcs.SDRecentMay 29, 2026

UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception

Yuhan Song, Linhao Zhang, Aiwei Liu, Chuhan Wu +5 more

UniAudio-Token is a framework that enhances existing semantic speech tokenizers with general audio perception, allowing them to handle diverse audio types while maintaining high-fidelity speech capabi…

View →
cs.CRcs.AIcs.CLRecentMay 28, 2026

Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage

Shahinul Hoque, Jinghuai Zhang, Jinyuan Sun, Fnu Suya

The paper demonstrates that the current per-token billing model for LLMs is susceptible to systematic overcharging because auditing frameworks must rely on evidence provided by the very companies that…

View →
cs.CRcs.AIcs.CLRecentMay 28, 2026

Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage

Shahinul Hoque, Jinghuai Zhang, Jinyuan Sun, Fnu Suya

The paper demonstrates that the current per-token billing model for LLMs is susceptible to systematic inflation because auditing frameworks must rely on evidence provided by the service provider, crea…

View →
cs.CLcs.DSRecentMay 29, 2026

Incremental BPE Tokenization

Shenghu Jiang, Ruihao Gong

The paper introduces an efficient, novel algorithm for incremental Byte Pair Encoding (BPE) tokenization that processes input text prefix by prefix, achieving significant speedups and enabling streami…

View →
cs.AIDatasetRecentJun 16, 2026

The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data

Nick Bettencourt, Xiaowei Ding, Kay Giesecke

The paper introduces the Stanford EDGAR Filings Dataset (SEFD), an open-source corpus of financial documents for training and evaluating large language models.

View →
cs.CREmpiricalRecentSep 25, 2026

FragToken: Amplifying LLM Inference Costs through Noncanonical Token Generation

Zihan Wang, Rui Zhang, Xinyuan Qian, Qingchuan Zhao +2 more

This paper proposes a method to induce fragmented generation in large language models to increase inference cost without degrading model utility.

View →
cs.CRRecentJun 1, 2026

Unicity: Predicates and Atomic Swaps

Ahto Buldas, Dirk Draheim, Mike Gault, Risto Laanoja +2 more

The paper generalizes Unicity token ownership using programmable spending conditions called predicates, enabling trustless atomic swaps and smart-contract-like functionality executed off-chain.

View →
cs.CVcs.AIRecentMay 28, 2026

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning

Geng Li, Guohao Chen, Ting Chen, Shilin Shan +5 more

OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM…

View →