Researcher

Sergio Arnaud

Meta FAIR

Role and affiliation as stated on the event page. Publication count is the dominant co-author cluster among 9 arXiv papers published under this name.

Recent work

• DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning
• Visuo-Tactile World Models
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D
• Unifying 2D and 3D Vision-Language Understanding
• From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs

From the resolved cluster. Most recent submission 2026-07-03.

Works on

Papers in this index

Matched on author name across this corpus only. Common names can collide, so tell us if one is wrong.