20 results for “soft tokens”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
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.
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…
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…
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…
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…
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…
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.
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.
Gasp is a decentralized exchange using optimistic rollup technology for gas-free, native cross-chain swaps with security guarantees and liquidity incentives.
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…
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…
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…
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…
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…
The paper introduces the Stanford EDGAR Filings Dataset (SEFD), an open-source corpus of financial documents for training and evaluating large language models.
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.
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.
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…