Website update - now at Rizlum AI, and a new ICIP paper
— Updates — 1 min read
I have updated my website to reflect my current role as an AI Research Scientist at Rizlum AI in Paris, where I work on multimodal document-understanding models, proprietary Speech-to-Text and Text-to-Speech models (sub-200 ms latency) and real-time speech-to-speech conversational voice agents.
I have also added our new paper, EmoMamba: Advancing Dynamic Facial Expression Recognition with Visual and Textual Fusion, published at ICIP 2025, to the Publications section, and refreshed my CV accordingly.