New multimodal model architectures shouldn't require new serving systems.
Introducing our work, M* (M-Star): a universal serving system for multimodal models that separates what a model computes - a dataflow graph - from how it runs: placement, scheduling, batching, and transport.
Joint work across @uwcse, @StanfordAILab, and @CMU_ECE with Atindra Jha, Naomi Sagan, Irmak Sivgin, Rohan Sanda, @ste_veng, Mark Horowitz, @LukeZettlemoyer, Olivia Hsu, @jure, @bariskasikci, and @thepadawang.
Many people think any given ML project is 99% training.
In reality, it’s 50% evaluation, 40% data cleaning, 8% integration, and 2% training.
The first two set the noise floor for learning. No ML magic matters; the model cannot lower the noise floor, as that’s the optimal bound of Shannon encoding of your data.
Thus, not a single day goes by without me thinking about ontology. Even the old labels have to be constantly reviewed.
New paper: Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
We use RL to post-train speech models (Moshi and PersonaPlex) to talk more like a human: to know when to respond, when to wait, and when to nod along with “yeah”s and “okay”s when listening.
People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the same way.
We share our approach, early results, and a quick look at our model in action.
https://t.co/AFJZ5kH7Ku