MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use Paper • 2608.20202 • Published 21 days ago • 34
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence Paper • 2608.12036 • Published 29 days ago • 87
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms Paper • 2607.26497 • Published Jul 30 • 52
MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing Paper • 2607.27616 • Published Jul 30 • 39
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement Paper • 2607.18217 • Published Jul 20 • 62
AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery Paper • 2511.11257 • Published Nov 14, 2025 • 25