Alex Bewley

Google (United States) — United States

Computer Science · Physical Sciences

20h-index9.4kcitations65works9.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Neural Network Applications(13), Video Surveillance and Tracking Methods(12), Advanced Image and Video Retrieval Techniques(10), Human Pose and Action Recognition(10), Robotics and Sensor-Based Localization(9)

Publications65 total

Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
arXiv (Cornell University)·2025Open Access
SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement
2025· 1 cited
Achieving Human Level Competitive Robot Table Tennis
2025· 1 cited
SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement
arXiv (Cornell University)·2025Open Access
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
arXiv (Cornell University)·2025Open Access
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
Lecture notes in computer science·2024· 5 cited
Linear Transformer Topological Masking with Graph Random Features
arXiv (Cornell University)·2024Open Access
Imitating Language via Scalable Inverse Reinforcement Learning
arXiv (Cornell University)·2024Open Access
Achieving Human Level Competitive Robot Table Tennis
arXiv (Cornell University)·2024· 3 citedOpen Access
Learning to Learn Faster from Human Feedback with Language Model Predictive Control
2024· 20 cited
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration<sup>0</sup>
2024· 98 cited
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
arXiv (Cornell University)·2024Open Access
Learning to Learn Faster from Human Feedback with Language Model Predictive Control
arXiv (Cornell University)·2024Open Access
Imitating Language via Scalable Inverse Reinforcement Learning
2024· 1 cited
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
arXiv (Cornell University)·2023· 101 citedOpen Access
Video OWL-ViT: Temporally-consistent open-world localization in video
2023· 10 cited
Robotic Table Tennis: A Case Study into a High Speed Learning System
arXiv (Cornell University)·2023· 1 citedOpen Access
Robots That Can See: Leveraging Human Pose for Trajectory Prediction
IEEE Robotics and Automation Letters·2023· 21 citedOpen Access
Video OWL-ViT: Temporally-consistent open-world localization in video
arXiv (Cornell University)·2023Open Access
Robotic Table Tennis: A Case Study into a High Speed Learning System
2023· 17 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Ben Upcroft(12), Ingmar Posner(8), Pannag Sanketi(7), Markus Wulfmeier(6), Anish Shankar(6), Saminda Abeyruwan(6), Laura Graesser(6), Cristian Sminchisescu(5), Heni Ben Amor(5), Vincent Vanhoucke(5), David B. D’Ambrosio(5), Vikas Sindhwani(5), Atıl Işçen(5), Krzysztof Choromański(5), Zongyuan Ge(4), Pei Sun(4), Dragomir Anguelov(4), Dorsa Sadigh(4), Kenneth Oslund(4), Hao-Tien Lewis Chiang(4)