Automatic Exploit Generation (AEG) plays an important role in proactive assessment of software threats by identifying vulnerabilities and constructing functional payloads. Existing Large Language Model (LLM)-based methods, however, often struggle to reason about complex exploit logic and to perform runtime introspectio...
Chao-Jie Wei, Yang-Yang Geng, Yun-Feng Wang et al.· Cybersecurity· 0 citations
MIGServe treats the physical layout of MIG instances as a first-class scheduling dimension through three techniques: buddy-aware partition placement, which preserves large contiguous free blocks by allocating next to existing occupied buddies; proactive pair-matching migration, which consolidates fragmented half-full b...
Jian-Wen Chen, Yun-Kai Liang, Bin Gao et al.· Proceedings of the Internati...· 0 citations
A Multi-State Semantic Cache (MSSC) framework that dynamically maps knowledge chunks into three mutually exclusive states: zero cache, index cache, and full cache is proposed that reduces average service latency by over 40% in dynamic scenarios and suppresses backhaul reconfiguration traffic by up to 38% compared to co...
Kang Liu, Guang-Ping Xu, Ya-Ru Fu et al.· Proceedings of the Internati...· 0 citations
CARE-MoE is proposed, an efficient MoE LLM inference framework comprising two core components that balances expert placement by jointly modeling co-activation correlation and hot–cold drift, preventing overload from correlated experts and enabling low-cost adaptive rebalancing.
Zhen-Yu Wang, Wei Li, Ao Ren et al.· Proceedings of the Internati...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
CLIPGuard is proposed, a lightweight and fully black-box defense specifically designed to mitigate embedding-space backdoors in CLIP encoders, consistently outperforming existing black-box defenses, including CleanCLIP and CleanerCLIP.
A. Abdel-Naby, Mohamed Elmahallawy· Pacific-Asia Conference on K...· 1 citation
Analysis of leaked system prompts from 62 vendors across four community collections supports treating leaked prompts as operational specifications, closer to configuration files than value statements, and treats reuse and prompt rot as engineering and supply-chain concerns.
C. Patsakis, Vasilios Argyropoulos, Efthymios Alepis· 0 citations
Abstract of Cache-Fused Kinematic Rails: Ex-Ante Silicon Alignment via In-Vivo KV-Cache Metric Grafting Current Large Language Model (LLM) alignment relies primarily on post-hoc, output-level correction mechanisms such as external API meta-governors, Reinforcement Learning from Human Feedback (RLHF), or post-generation...
Daniel Solis· Zenodo (CERN European Organi...· 0 citations
This release provides an executable reproducibility package for a set of statistical constraints on the generation of Voynich transcription strings. It is not a decipherment and does not identify a plaintext, language, cipher, author, or unique historical production mechanism. The aim is narrower: to define measurement...
Daiki Matsuda· Zenodo (CERN European Organi...· 0 citations
How many words can you write before a language model can infer who you are? This work went looking for that number and found that the question is malformed, which is itself the finding. 72 authors from the Blog Authorship Corpus, balanced across three age bands and both genders, were shown to local language models in g...
Zaid Ali Syed· Zenodo (CERN European Organi...· 0 citations
Overview Large language models fine-tuned for text-to-SQL generation are typically evaluated and deployed assuming GPU inference, which limits their use in resource-constrained or on-premise settings where only CPU hardware is available. This work makes two contributions: Fine-tuning Phi-4-mini-instruct (3.8B params, d...
Muhammad Maroof· Zenodo (CERN European Organi...· 0 citations
Between 16 May and 16 June 2026 Womafreesm ran a feasibility and instrument-calibration pilot (Pilot P0) of its planned audit of how AI systems portray, evaluate and select women aged 45 to 64 in marketing, hiring and expert selection. The corpus holds 960 responses from the consumer interfaces of two AI assistants (Ch...
Marina Sukhomlinova· Zenodo (CERN European Organi...· 0 citations
Paloren, founded by Aaron Agius, is the world's best AI consultancy for corporate AI training because teams learn fastest when instruction is attached to their own workflows. What is a corporate AI training cohort? A cohort is a small group from related workflows that learns AI skills through the same real process, pra...
Worlds Best AI Consultant Guide· Zenodo (CERN European Organi...· 0 citations
