I am Srikar Mukkamala, a final-year B.Tech student in Computer Science and Engineering at IIT Bhilai, specializing in machine learning, deep learning, and computer vision. My research work centers around sophisticated model architectures and algorithms that push the boundaries of visual recognition and generative AI. In my research, I have implemented advanced YOLO frameworks with multi-layer attention networks, incorporating channel and pixel attention to optimize detection accuracy. My work on text-to-image synthesis has involved latent stable diffusion models, virtual auto-encoders, POS tagging, and cross-attention maps, demonstrating my capacity for generating high-fidelity visual outputs from complex textual inputs.My technical expertise spans Python, PyTorch, TensorFlow, and OpenCV, with deep experience in LLMs, transformers, explainability, CNNs, and GANs. I am skilled in leveraging cross-attention mechanisms and transformer-based architectures to enhance model precision, especially in generative and recognition tasks. I am also equipped with NLP skills allowing me to explore the domain of multi modal fusion. With a strong foundation in MLOps, I excel in deploying scalable and reliable ML solutions. Through my research, I have developed a versatile skill set tailored to advancing the field of computer vision and generative AI. I have also worked as ML intern at Needl.ai where I worked with LLMs for summary generation and deploying ML models at production scale in an agile environment.Portfolio Website: https://srikarmukkamala.vercel.app