Ya Zhang

Entity-aware comparative reasoning can be learned from routine clinical data, leading to significant improvements in diagnostic accuracy and retrieval performance in radiology.

Static benchmarks fail to predict LLM performance in dynamic clinical settings, with top models only achieving 60.4% of expert criteria in real-world simulations.

PEFT can enable the creation of millions of personalized models, each with unique adaptations, leveraging the power of trillion-parameter foundation models.

LLMs can safely guide DRL exploration in autonomous driving, leading to faster convergence and improved performance compared to traditional DRL methods.

Forget PEFT and KD, reprogramming distillation offers a surprisingly effective and robust way to adapt large medical foundation models to diverse downstream tasks.

ALMs can now pinpoint sounds in time with far greater accuracy, thanks to a new training method that stops them from hallucinating timestamps.