MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes Paper • 2609.10016 • Published 23 days ago • 29
EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal Paper • 2608.05565 • Published Aug 6 • 23
Weak-to-Strong Generalization via Direct On-Policy Distillation Paper • 2607.05394 • Published Jul 8 • 144