Didactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models Paint-Anything: Unified Any-Color Control for Image Generation and Editing