Home » Teams » ACIDE » Silvia Tulli

  • Silvia Tulli

  • Assistant Professor
  • Team: ACIDE
  • Office: J05
  • Email: slvtulli@gmail.com
  • Phone:0623539830
  • Addresse: Pyramide - T55, 4 Pl. Jussieu 65, 75005
  • Bio: I am interested in developing algorithms to allow AI systems to better learn and collaborate with humans. I worked on inverse RL approaches to enable machine learning from contrastive examples and I’m interested in extending this work to incorporate human modeling and enhance AI alignment.

Publications

  • Sebastian Wallkötter, Silvia Tulli, Ginevra Castellano, Ana Paiva, Mohamed Chetouani. Explainable Embodied Agents Through Social Cues: A Review. ACM Transactions on Human-Robot Interaction, 2021, 10 (3), ⟨10.1145/3457188⟩. ⟨hal-03152010⟩
    [ HTTP | PDF ]
  • Silvia Tulli, Sebastian Wallkötter, Ana Paiva, Francisco Melo, Mohamed Chetouani. Learning from Explanations and Demonstrations: A Pilot Study. 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, Dec 2020, Dubin, Virtual, Ireland. pp.61-66. ⟨hal-03152179⟩
    [ HTTP ]