Amandine Brunetto

Ph.D. Candidate
Mines Paris, PSL University

Email: amandine.brunetto[AT]minesparis.psl.eu

photo_brunetto.png

I’m a final-year PhD student at PSL Research University, working at the Center for Robotics at Mines Paris. My research focuses on multimodal learning with a focus on how combining the audio and visual modalities can enhance perception.

My passion for audio runs deep—I’m also a musician—which naturally led me to explore how sound interacts with visual information in learning systems. Recently, I worked on NeRAF, a method for implicit acoustic learning based on 3D scenes that generates spatial room impulse responses at novel viewpoints (ICLR 2025). I also contributed to the Audio-Visual Batvision dataset, which addresses depth prediction from robot-generated echoes (IROS 2023).

Broadly, I’m interested in multimodal generation, audio & computer vision, neural implicit learning and increasingly, diffusion models.

In a few months, I’ll be looking for exciting opportunities, either as a research scientist in an industrial lab or in a postdoctoral position, where I can keep pushing the boundaries of multimodal AI. Feel free to reach out if you’re interested in collaborating, chatting about research, or if you know of opportunities that align with my work.

Selected Publications

  1. NeRAF_concept.png
    NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields
    Amandine BrunettoSascha Hornauer, and Fabien Moutarde
    In The Thirteenth International Conference on Learning Representations, 2025
  2. WAM.png
    One Wave to Explain Them All: A Unifying Perspective on Post-hoc Explainability
    Gabriel KasmiAmandine BrunettoThomas Fel, and Jayneel Parekh
    2024
  3. IROS23_Graphical_Abstract.png
    The Audio-Visual BatVision Dataset for Research on Sight and Sound
    Amandine BrunettoSascha HornauerStella X. Yu, and Fabien Moutarde
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
  4. PANOECHO_concept.png
    PANO-ECHO: PANOramic depth prediction enhancement with ECHO features
    Xiaohu Liu, Amandine BrunettoSascha HornauerFabien Moutarde, and Jialiang Lu
    In IEEE Conference on Artificial Intelligence (CAI), 2024