The paper introduces CFGzip, an offline token space compression technique that significantly reduces the computational overhead of constrained decoding, making complex grammar enforcement feasible at…

This paper introduces Byte-Prefix Marginalization (BPM), a method for consolidating open-weight language models through on-policy distillation while preserving teacher probability mass and maintaining…

The paper argues that large language models (LLMs) are a special case of world models and proposes a continuous spectrum between token prediction and latent-space architectures.

PASA introduces a robust, semantic-level watermarking technique that embeds and detects watermarks in the latent embedding space, successfully resisting semantic-invariant attacks like paraphrasing.

The paper proposes a unified framework for designing efficient and expressive token mixing layers by separating the direct and recurrent influences of inputs, allowing for a principled trade-off betwe…

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…

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 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…

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…

This paper compares three methods for answering questions over legal documents: full-corpus injection, embedding retrieval, and LLM navigation over a compact structured index. The results show that th…

PARCEL introduces a novel visual tokenization architecture that combines spatial pooling anchors with conditioned elastic queries, efficiently reducing the computational cost of large Vision-Language…

The paper introduces the concept of 'host-space perturbations,' arguing that real-world attackers can only manipulate network inputs by controlling specific hosts, a constraint that significantly weak…

PHANTOM is a novel framework that generates highly convincing, context-aware honeytokens by incorporating deep organizational knowledge, significantly improving their believability and detection resis…

The paper proposes a novel global sketch-based watermarking technique for diffusion language models that controls the entire sequence's statistics, offering an order-agnostic and context-independent a…

This study uses a BERT-based LLM to analyze Discord sentiment and combines it with financial data to build a multi-modal model that significantly improves the prediction of Decentraland's MANA token p…

This paper compares the preservation of linguistic content in different text encodings (tokens, bytes, pixels) using a shared bottleneck, revealing their distinct strengths in surface form preservatio…

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