Chau Yuen

Jointly pruning dependent units in LLMs can lead to more effective model compression without the need for fine-tuning, challenging conventional independent pruning methods.

Covert AUV missions can achieve up to 30% greater task efficiency by leveraging a new framework that optimizes the value of sensed information under communication constraints.

Bridging satellite imagery with street-level semantics boosts urban carbon emission predictions, achieving superior accuracy without needing ground-level data at inference.