Victor Morand
Hi ! I’m Victor, currently PhD Student working in the MLIA team of the Institute of Intelligent Systems and Robotics (ISIR) located in Sorbonne Université, under the supervision of Benjamin Piwowarski and Josiane Mothe.
🎓 Towards Language models that know what they know
My thesis is entitled Domain adaptation in Pretrained Language Models, Applications to information retrieval and Conversational search. Put more simply, we aim at improving Information Retrieval and access using the emerging ability of Pretrained Language Models to understand text.
📄 Featured Publications
We reproduce and compare different distillation strategies for cross-encoders across a wide range of architectures, identifying robust design choices for effective re-ranking.
We propose MICE (Minimal Interaction Cross-Encoders), a new architecture that achieves a 4x decrease in inference latency while maintaining high ranking effectiveness.
We introduce ToMMeR, a lightweight model probing mention detection capabilities from early LLM layers, achieving high zero-shot recall across diverse benchmarks.
We investigate how Large Language Models internally represent entities by introducing entity mention reconstruction as a novel framework for studying how LLMs encode and manipulate entities.
We study the numerical approximation of scalar conservation laws by computational optimization of the numerical flux function in a first-order finite volume method.