content type videopublished June 18, 2025
Apple Workshop on Human-Centered Machine Learning 2024: Tiny but Powerful: Human-Centered Research to Support Efficient On-Device ML
AuthorsMary Beth Kery
Related readings and updates.
Locking Pretrained Weights via Deep Low-Rank Residual Distillation
August 6, 2026research area Methods and Algorithms
The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling their use across diverse hardware and software platforms. They also allow for more open research and testing, to the extent that users can use them as checkpoints, fine-tune them according to their needs, and potentially redistribute them. In some cases, however, concerns on modifying these weights…
DeepAmbigQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness
August 6, 2026research area Knowledge Bases and Search, research area Speech and Natural Language Processing
Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such as “Which actor from the film Heat won at least one Academy Award?”, which requires (1) distinguishing between multiple films sharing the same title and (2) reasoning across a large set of actors to gather and integrate evidence. Existing QA…
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.