Muhammad Muaz

👋 Hi, I’m Muaz!

🧑🏻‍💻 About Me¹

💻 currently a computer science graduate student @ (UT Austin).

🚀 generatly interested in application of AI/ML specifically in domains of Generative AI (Diffusion Models), 3D Vision, & Multi-Modality²

📝 Resume

You can check out my resume here

📒 Recent Posts

You can checkout list of recent posts here

👀 If you’re curious
- 📍 My current research & How I got here
  
  My Ph.D. is currently focused on techniques to optimize the inference complexity of deep generative models such as SVD, Latte. In 🧍terms, I try to make these models run faster.
  
  Recently in May 2024, I also completed my Masters 🎓 in Computer Science from (UT Austin). 🎉🎉
  
  Prior to this, I completed bachelors degree (Electrical Engineering, 2021) at the Lahore University of Management Sciences LUMS. My undegraduate dissertation was titled Vibration Estimation and Object Localization using RFID Technology in Challenging Environments. !!

Conditioning Diffusion Models with 3D Human Shape
Learning for 3D Humans Course Project, 2024
Comparative Analysis of Multi-Modal Large Language Models (LLM)
Topics in Natural Language Processing, 2023
Bridging Modalities: Knowledge Distillation and Masked Training for Translating Multi-Modal Emotion Recognition to Uni-Modal, Speech-Only Emotion Recognition
Muaz, M. et al., [arXiv:2401.03000]

generative-models 🤖: Diffusion Models, generative-models
OpenSTL 🎞️: Spatio-Temporal Learning + Prediction
Cogmen_SLT 🔊 [web]: Emotion Recognition, Multimodal -> Speech only

tomesd 🗜️: Token Merging & Optimization for diffusion model/s speedup
diffusers 🧨: Fork of diffusers library

GitHub Stats

GitHub Stats (m-muaz):

Table 1: 🎓 Education

Table 1: 🎓 Education

Last Updated: 10/21/2024 @ 03:31:23