content type videopublished August 29, 2024
Apple Workshop on Privacy-Preserving Machine Learning: Interactive Differential Privacy in the OpenDP Library
AuthorsSalil Vadhan (Harvard University, U. Sydney)
Related readings and updates.
From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers
August 27, 2026research area Methods and Algorithms, research area Speech and Natural Language Processing
Designing effective reward signals for open-domain question answering is challenging because high-quality responses must simultaneously satisfy multiple aspects of answer quality that are difficult to capture with a holistic scalar objective. We introduce a rubric-based reward framework that generates query-specific rubrics grounded in retrieved evidence and decomposed into multiple quality dimensions, providing fine-grained supervision during…
PROOF-Gen: From Optimized Data to Better Distillation
August 26, 2026research area Speech and Natural Language Processing, research area Tools, Platforms, Frameworksconference EMNLP
Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Post-training pipelines that drive shipped tool-calling agents re-run this stage on a daily or weekly cadence, paying the frontier-teacher cost each cycle, yet the mechanism is generate-and-filter (keep the teacher’s passing trajectories, discard the rest) and each cycle leaves behind the same hard…
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.