Recent & Upcoming Talks

Discuss the recent NeurIPs'2024 paper from our lab on joint network/protocol optimization to enable efficient private Transformer inference.

Discuss the recent works from our lab on joint network/protocol optimization to enable more efficient privacy-preserving AI.

Discuss the recent works from our lab on full stack optimization to enable accurate yet efficient AI acceleration for multi-modal applications.

Discuss the recent works from our lab on full stack optimization to enable accurate yet efficient AI acceleration for multi-modal applications.

Discuss full stack techniques from training, optimization, hardware, etc perspectives to enable efficient audio-visual understanding on AR devices

Discuss full stack techniques from training, optimization, hardware, etc perspectives to enable efficient audio-visual understanding on AR devices

Discuss our recent progress on improving the weight-sharing NAS by designing better search space and better supernet training algorithms