Tootfinder

TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving
Bingyang Wu, Zili Zhang, Yinmin Zhong, Guanzhe Huang, Yibo Zhu, Xuanzhe Liu, Xin Jin
https://arxiv.org/abs/2508.17219

TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving
Prefix caching is crucial to accelerate multi-turn interactions and requests with shared prefixes. At the cluster level, existing prefix caching systems are tightly coupled with request scheduling to optimize cache efficiency and computation performance together, leading to load imbalance, data redundancy, and memory fragmentation of caching systems across instances. To address these issues, memory pooling is promising to shield the scheduler from the underlying cache management so that it can …

CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs
Jianting Tang, Yubo Wang, Haoyu Cao, Linli Xu
https://arxiv.org/abs/2508.06917 ht…

CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs
Recent advances in molecular science have been propelled significantly by large language models (LLMs). However, their effectiveness is limited when relying solely on molecular sequences, which fail to capture the complex structures of molecules. Beyond sequence representation, molecules exhibit two complementary structural views: the first focuses on the topological relationships between atoms, as exemplified by the graph view; and the second emphasizes the spatial configuration of molecules, …

Execution and monitoring of HOA automata with HOAX
Luca Di Stefano
https://arxiv.org/abs/2507.11126 https://arxiv.org/pdf/2507.11126

Execution and monitoring of HOA automata with HOAX
We present a tool called Hoax for the execution of ω-automata expressed in the popular HOA format. The tool leverages the notion of trap sets to enable runtime monitoring of any (non-parity) acceptance condition supported by the format. When the automaton is not monitorable, the tool may still be able to recognise so-called ugly prefixes, and determine that no further observation will ever lead to a conclusive verdict. The tool is open-source and highly configurable. We present its formal foun…

InfoFlood: Jailbreaking Large Language Models with Information Overload
Advait Yadav, Haibo Jin, Man Luo, Jun Zhuang, Haohan Wang
https://arxiv.org/abs/2506.12274

InfoFlood: Jailbreaking Large Language Models with Information Overload
Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by adversarial techniques known as "jailbreak" attacks. Existing jailbreak methods typically involve appending carefully crafted prefixes or suffixes to malicious prompts in order to bypass the built-in safety mechanisms of these models. In this work, we identif…