Ashim Dahal is a passionate and results-driven Machine Learning Researcher with expertise in computer vision with Deep Learning, specializing on generative computer vision.

His research interests include but not limited to stable diffusion, language guidance for vision models, multimodal systems, video understanding, parallel computing, 3D reconstruction, mesh understanding, vision transformers and zero-shot generalization for vision models.

Since 2019, Ashim has been dedicated to researching and advancing his knowledge in the field of ML and DL, focusing specifically on SotA deep learning techniques.