Submitted by akhaliq 27 Tora: Trajectory-oriented Diffusion Transformer for Video Generation · 5 authors 2
Submitted by VictoriaLinML 22 MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts · 8 authors 5
Submitted by xuuuluuu 18 Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent · 7 authors 8
Submitted by sileod 8 TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods · 5 authors 2
Submitted by akhaliq 8 Berkeley Humanoid: A Research Platform for Learning-based Control · 6 authors 2
Submitted by akhaliq 4 NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields · 6 authors 2