RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published Oct 1 • 37
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Paper • 2609.34981 • Published Sep 29 • 80
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation Paper • 2609.36601 • Published Sep 29 • 24