About me

I’m Théo Gigant, a PhD student exploring the capabilities of language models and vision-language models to comprehend and summarize multimodal documents such as videoconference records.

What to Expect from this Blog

On this blog, I’ll be sharing some insights on my own research, as well as some reflections and opinions about Natural Language Processing, Computer Vision and Artificial Intelligence.

Stay Connected

If you’re interested in discussing , I invite you to connect with me on Twitter, LinkedIn, HuggingFace, or reach out to me directly with questions, comments, or collaboration ideas at my email.