Similar Items: GMGaze: MoE-Based Context-Aware Gaze Estimation with CLIP and Multiscale Transformer
- TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning
- MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems
- MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons
- MoCoTalk: Multi-Conditional Diffusion with Adaptive Router for Controllable Talking Head Generation
- Accelerating MoE with Dynamic In-Switch Computing on Multi-GPUs
- Linearizing Vision Transformer with Test-Time Training