← Search

Mani Malek

2 accepted papers

2026

The ACE Protocol: Operationalizing Language Model Activations for Better Calibration and Utility

ICML 2026poster

As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential. Calibration is a good proxy for trust: well-calibrated confidence estimates help inform the risk versus reward trade-off when trusting a specific model output. Unfortunately, e…

Cited by 0SourceScholar
2022

Federated Learning with Buffered Asynchronous Aggregation

AISTATS 2022poster

Scalability and privacy are two critical concerns for cross-device federated learning (FL) systems. In this work, we identify that synchronous FL – cannot scale efficiently beyond a few hundred clients training in parallel. It leads to diminishing returns in model performance and training speed, ana…

Cited by 377SourcePDFScholar