3 accepted papers
Normative theories allow one to elicit key parts of a ML algorithm from first principles, which is crucial at a time of championed scrutiny for ML work. Direct Preference Optimization (DPO) cleverly bypasses reward modeling by making an explicit link with a specific normative model of human choice. …
Despite the growing reasoning capabilities of recent large language models (LLMs), their internal mechanisms during the reasoning process remain underexplored. Prior approaches often rely on human-defined concepts (e.g., overthinking, reflection) at the word level to analyze reasoning in a supervise…
Federated learning has been deployed to train machine learning models from decentralized client data on mobile devices in practice. The clients available for training are observed to have periodically shifting distributions changing with the time of day, which can cause instability in training and d…