Tal Remez Ph.D
talremez at gmail dot com
|
I am an AI and machine learning researcher with a PhD and experience across a variety of fields, including large language models (LLMs), optimization, visual perception, computational photography, and audio-visual methods for speech enhancement. My work has focused on applications of LLMs in audio and music generation, as well as text and code generation. Recently, I’ve explored techniques like flow matching and diffusion in latent text embeddings for tasks like chain-of-thought reasoning. With a background at Facebook AI Research (FAIR) and Google Research, I’ve led projects that pushed the boundaries of AI, including on-device audio-visual speech separation and advancements in LLMs. I’m now looking for my next challenge where I can apply my skills and collaborate with a talented team to drive meaningful outcomes. |
Publications
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|