Chief Scientist, Twenty Billion Neurons
2 papers at NeurIPS 2025
We show that multiplicative (bi-linear) hidden state transitions are a natural choice for representing state tracking behavior in linear recurrent networks.
Current multi-modal LLMs struggles with live, step-by-step task guidance. We built Qualcomm Interactive Cooking (a new dataset with mistake videos and timed feedback) and LiveMamba (a streaming model) to enable better real-time interactive guidance.
