I am a PhD student with interest in the fields of generative models and audio processing and I have a strong track record of developing innovative solutions to complex problems.

My work has focused on enabling source separation using latent autoregressive models in VQ-VAE domains, proposing a Bayesian sampling technique based on fully discrete likelihood functions. I pursued an internship at Dolby Laboratories where I improved universal sound separation using adversarial techniques. I have combined my expertise in music generation and source separation to develop a diffusion-based model that can perform both tasks simultaneously.

I am committed to pushing the boundaries of what is possible in the field and am eager to continue making impactful contributions.