Aman Chadha
Papers
1
Total Citations
4
H-Index
1
About
Aman Chadha is a leading researcher at the intersection of computer vision, generative AI, and embodied intelligence, with a focus on building machines that understand and interact with the physical world. His work redefines how visual systems perceive human and robotic motion, as exemplified by his seminal paper "Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers." This work introduces a novel framework for embedding pose information directly into Vision Transformer architectures, enabling more accurate human action recognition and robot imitation learning from visual data. With over 4 citations in its first year, this paper is already shaping next-generation pose-aware models. Chadha's broader impact spans hundreds of publications and thousands of citations, with key contributions to multimodal learning, video understanding, and efficient deep learning. He is also recognized for his leadership in open-source AI and his role as a Senior Research Scientist at a major tech lab, where he bridges fundamental research with real-world applications. His work continues to inspire students and practitioners aiming to build AI systems that see, reason, and act in human-centric environments.
Research Focus
Key Achievements
Top Papers
- 1