Multimodal Safety Evaluation in Generative Agent Social Simulations Paper • 2510.07709 • Published 16 days ago • 13
Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation Paper • 2509.21989 • Published 29 days ago • 22
Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale Paper • 2509.14008 • Published Sep 17 • 87
Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic Paper • 2509.01363 • Published Sep 1 • 57
Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection Paper • 2508.20766 • Published Aug 28 • 14
Train Long, Think Short: Curriculum Learning for Efficient Reasoning Paper • 2508.08940 • Published Aug 12 • 26
An Embarrassingly Simple Defense Against LLM Abliteration Attacks Paper • 2505.19056 • Published May 25 • 6