Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model Paper • 2607.03509 • Published 11 days ago • 14
From Foundation to Application: Improving VLA Models in Practice Paper • 2607.06403 • Published 7 days ago • 18
Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory Paper • 2605.17478 • Published May 17 • 1
Learning Transferable Visual Models From Natural Language Supervision Paper • 2103.00020 • Published Feb 26, 2021 • 22 • 5
VISReg: Variance-Invariance-Sketching Regularization for JEPA training Paper • 2606.02572 • Published Jun 1 • 4