Agent-Editing World Model: Rethinking World Modeling for LLM Agents Paper • 2609.28416 • Published 7 days ago • 39
Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models Paper • 2609.21094 • Published 13 days ago • 6
MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads Paper • 2609.09206 • Published 25 days ago • 11