Pierre Sermanet

Computer Science · Physical Sciences

30h-index55.5kcitations80works17.32yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Multimodal Machine Learning Applications(26), Domain Adaptation and Few-Shot Learning(20), Robot Manipulation and Learning(19), Human Pose and Action Recognition(19), Advanced Image and Video Retrieval Techniques(17)

Publications78 total

Gemini Robotics: Bringing AI into the Physical World
arXiv (Cornell University)·2025· 4 citedOpen Access
SciFi-Benchmark: Leveraging Science Fiction To Improve Robot Behavior
arXiv (Cornell University)·2025Open Access
Generating Robot Constitutions & Benchmarks for Semantic Safety
arXiv (Cornell University)·2025Open Access
Predictive Red Teaming: Breaking Policies Without Breaking Robots
arXiv (Cornell University)·2025Open Access
A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
arXiv (Cornell University)·2024Open Access
RT-H: Action Hierarchies using Language
2024· 40 cited
Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers
2024· 22 cited
RoboVQA: Multimodal Long-Horizon Reasoning for Robotics
2024· 30 cited
Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers
arXiv (Cornell University)·2024Open Access
RT-H: Action Hierarchies Using Language
arXiv (Cornell University)·2024Open Access
AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents
arXiv (Cornell University)·2024· 14 citedOpen Access
RoboVQA: Multimodal Long-Horizon Reasoning for Robotics
arXiv (Cornell University)·2023· 2 citedOpen Access
Video Language Planning
arXiv (Cornell University)·2023· 3 citedOpen Access
Robotic Table Tennis: A Case Study into a High Speed Learning System
arXiv (Cornell University)·2023· 1 citedOpen Access
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
arXiv (Cornell University)·2023· 262 citedOpen Access
Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models
2023· 29 citedOpen Access
Robotic Table Tennis: A Case Study into a High Speed Learning System
2023· 17 citedOpen Access
Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations
2023· 7 cited
PaLM-E: An Embodied Multimodal Language Model
arXiv (Cornell University)·2023· 348 citedOpen Access
Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models
arXiv (Cornell University)·2022· 2 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Corey Lynch(16), Yann LeCun(15), Sergey Levine(13), Jonathan Tompson(11), Debidatta Dwibedi(10), Yevgen Chebotar(7), Karol Hausman(7), Brian Ichter(7), Raia Hadsell(7), Vincent Vanhoucke(6), Jasmine Hsu(6), Alper Nabi Erkan(6), Urs Müller(6), Pannag Sanketi(6), Koray Kavukcuoglu(5), Fei Xia(5), Quan Vuong(5), Marco Scoffier(5), Tianli Ding(5), Michaël Mathieu(4)