Characterizing the 14-dimensional solutions space of the power market optimization problem
As a quantitative researcher at Engie, I’ve worked on optimization problems. 
Posts by Collection
portfolio
portfolio-software
3D-Scene-Language to Action Model
Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy. 
Brio - AI-powered Job Interview Prep
Fullstack web development of an application helping candidates prepare for their job interviews. 
Characterizing the 14-dimensional solutions space of the power market optimization problem
As a quantitative researcher at Engie, I’ve worked on optimization problems.
Athena - Enterprise Resource Planning (ERP) of a student-led consulting firm
During my first year of master, I contributed to build the best ERP existing in France for student-led consulting firms. 
publications
Identifying Human Grasp Properties During Robot-to-Human Handover
Published in IEEE World Haptics Conference, 2023
TLDR; An efficient System Identification method during Robot-to-Human Handover for giving the robot quantitative information that it could use to decide when to safely let go of the object.
Recommended citation: Paul Pacaud, Etienne Chassaing, Yilin Cai, Connor Yako, and Kenneth Salisbury https://ieeexplore.ieee.org/abstract/document/10224405
Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation
Published in CoRL 2025 LEAP Workshop, 2025
TLDR; Gondola introduces a grounded vision-language planning model that uses multi-view images to generate precise action plans with segmentation masks for generalizable robotic manipulation, achieving state-of-the-art performance on the GemBench benchmark.
Recommended citation: Shizhe Chen, Ricardo Garcia, Paul Pacaud, and Cordelia Schmid https://arxiv.org/abs/2506.11261
Guardian: Detecting Robotic Planning and Execution Errors with Vision-Language Models
Published in CoRL 2025 Workshop Robot Data, 2025
TLDR; Guardian introduces an automatic robot failure synthesis approach that generates diverse planning and execution failures with fine-grained reasoning traces. We train a VLM that achieves state-of-the-art performance on failure detection benchmarks and effectively improves task success rates in both simulation and real robots.
Recommended citation: Paul Pacaud, Ricardo Garcia, Shizhe Chen, and Cordelia Schmid https://arxiv.org/abs/2512.01946
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.