real-time inference
- ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality
- Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
- LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers
- OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking