Daniele Paliotta

Hi 👋 ! I’m Daniele. I am a Member of Technical Staff at Cartesia, where I work on multimodal and TTS foundation models (transformers, state space models, linear RNNs) with a strong focus on efficiency.

I hold a PhD from the Machine Learning Group at the University of Geneva, where I was supervised by François Fleuret. My research focused on transformers, LLM systems and efficiency, and alternative architectures.

During my PhD, I was a research intern at Cartesia and a researcher at Together AI supervised by Tri Dao, where I worked on LLM distillation, efficient inference, and developed speculative decoding for Mamba/linear RNNs.

In a previous life, I have worked as a software engineer, I have done machine learning at Truelayer, and I have played in Capture the Flag competitions.

I also love sailing, reading, writing fiction, cooking and playing guitar.

You can follow me on Twitter, or find me on Linkedin.