arXiv:2609.02440v1 Announce Type: cross Abstract: Adversarially robust models often overfit to a specific attack budget, necessitating multiple…
Author: script
Addressing Trust in AI Systems through Education: A Didactic Perspective
arXiv:2609.02453v1 Announce Type: cross Abstract: Machine learning (ML) education faces two persistent and connected obstacles: many educational tools…
Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking
arXiv:2609.02414v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet…
Pentagon Official Reaffirms Anthropic Supply Chain Risk Designation
A senior Pentagon official on September 3, 2026 said Anthropic remains a designated supply chain risk to national security, days after a federal judge…
Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression
arXiv:2609.02451v1 Announce Type: cross Abstract: In this paper, we propose a scalable Kronecker-based approximation that captures cross-layer…
MAI-Transcribe-2 Tops FLEURS Benchmark Across 60 Languages, Microsoft Says
Microsoft AI released MAI-Transcribe-2 on September 3, 2026, a speech recognition model the lab said ranks first on the FLEURS benchmark across 60…
Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment
arXiv:2609.02417v1 Announce Type: cross Abstract: Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal…
Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts
arXiv:2609.02404v1 Announce Type: cross Abstract: Sparse mixture-of-experts (MoE) models use an independently parameterized router at each sparse layer to…
NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning
arXiv:2609.02366v1 Announce Type: cross Abstract: Named Entity Recognition (NER) has achieved substantial progress since the advent of large language…
MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts
arXiv:2609.02379v1 Announce Type: cross Abstract: While existing work on LLM authorship attribution (AA) has made progress, available benchmarks remain…