arXiv:2609.03693v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through…
Category: AI
Molecular D\’ej\`a Vu: Digit-Level Retrieval of Published Values in Frontier Language Models
arXiv:2609.05381v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on molecular property benchmarks, but accuracy…
CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents
arXiv:2609.05374v1 Announce Type: new Abstract: Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly…
Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe
arXiv:2609.05395v1 Announce Type: new Abstract: Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise…
Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence
arXiv:2609.05385v1 Announce Type: new Abstract: LLM decision components that can operate within agent workflows often produce action-relevant…
Who Should Grade My Work? Student Perspectives on Transparent AI-Assisted Writing Assessment in Higher Education
arXiv:2609.05346v1 Announce Type: new Abstract: The integration of GenAI tools into higher education assessment raises important questions about how…
9kV Solid-State Transformer Anchors Hyosung’s U.S. AI Grid Push
Hyosung Heavy Industries said on September 7, 2026, that it is accelerating its push into the U.S. AI data center power market, combining the 22.9kV…
LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagrams
arXiv:2609.05327v1 Announce Type: new Abstract: Quantum circuits are central to implementing quantum algorithms on quantum devices, where quantum gates…
New York City bans AI tools from public schools through eighth grade
New York City bans AI use in public schools through the end of middle school. The article New York City bans AI tools from public schools through eighth…
Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models
arXiv:2609.05333v1 Announce Type: new Abstract: A transformer language model assigns a single, context-independent vector to a word type at its embedding…