Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training Paper • 2607.01763 • Published 25 days ago • 10
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models Paper • 2606.11324 • Published Jun 9 • 172
FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning Paper • 2605.22552 • Published May 21 • 2