Research highlights
The "Super Weight:" How Even a Single Parameter can Determine a Large Language Model's Behavior
August 21, 2025
A recent paper from Apple researchers, "The Super Weight in Large Language Models," reveals that an extremely small subset of parameters in LLMs (in some cases, a single parameter) can exert a disproportionate influence on an LLM’s overall functionality (see Figure 1). This work highlights the critical role of these “super weights” and their corresponding “super activations,”...
FastVLM: Efficient Vision Encoding for Vision Language Models
July 23, 2025research area Computer Vision
Vision Language Models (VLMs) enable visual understanding alongside textual inputs. They are typically built by passing visual tokens from a pretrained vision encoder to a pretrained Large Language Model (LLM) through a projection layer. By leveraging the rich visual representations of the vision encoder and the world knowledge and reasoning capabilities of the LLM, VLMs can be useful for a wide range of applications, including accessibility...
Recent publications
Events
Apple Workshop on Privacy-Preserving Machine Learning 2025
August 12, 2025
Apple believes that privacy is a fundamental human right. As AI experiences become increasingly personal and a part of people's daily lives, it's important that novel privacy-preserving techniques are created in parallel to advancing AI capabilities.
Apple is presenting new work at the annual Interspeech conference, which takes place in person from August 17 to 21, in Rotterdam, Netherlands. Interspeech focuses on research surrounding the science and technology of spoken language processing.
Below is the schedule of Apple-sponsored workshops and events at Interspeech 2025.