Sergio Arnaud

5 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 👥 Mega-Team · Squad ❓ The Questioner

Venues

ICML (3) CVPR (1) NeurIPS (1)

Top co-authors

Franziska Meier (5) Alexander Sax (4) Aravind Rajeswaran (4) Oleksandr Maksymets (4) Ayush Jain (3) Arjun Majumdar (3) Paul Mcvay (3) Ada Martin (3) Vincent-Pierre Berges (3) Mikael Henaff (2)

Research topics

Machine Learning (4) Computer Vision (3) Learning Types (3) Deep Learning (2) Analysis (2) Artificial Intelligence (1) Natural Language Processing (1) Robotics (1) Applications (1) Architectures (1) Capabilities (1) Core AI (1) Core Methods (1) Domain-Specific (1) Techniques (1)

Keywords

point cloud (2) foundation model (2) referential grounding (2) instance segmentation (1) embodied ai (1) episodic memory (1) natural language (1) world model (1) egocentric video (1) active exploration (1) embodied question answering (1) mask decoder (1) vision-language understanding (1) gaussian representation (1) masked autoencoding (1) 2d-to-3d lifting (1) clip (1) render-supervised distillation (1) embodied systems (1) ground-truth object proposals (1)

Papers

From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs ICML 2025 LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D ICML 2025 Unifying 2D and 3D Vision-Language Understanding ICML 2025 OpenEQA: Embodied Question Answering in the Era of Foundation Models CVPR 2024 Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence? NeurIPS 2023