Generative AI for Vision & Avatars
Applying GANs, diffusion models, and NeRF-based methods to build visual AI systems, including talking-head avatars, facial animation pipelines, and generative workflows for medical image analysis.
Tools and frameworks I use to build applied AI systems, generative AI solutions, and intelligent products.
Doctoral research focused on applied AI, avatar-based training systems, generative visual models, and human-AI interaction.
Download PhD ThesisAI product company developing interactive training and digital learning solutions
- Built a RAG-based chatbot system for Krifa, integrating document retrieval, LLM-powered response generation, and a user-facing chat interface to improve access to company knowledge. - Contributed to the development of Ågo Course, a full-stack interactive training platform, focusing on Python backend development and AI components within a Next.js/React-based product stack. - Created AI-generated training videos with Google Veo and designed interactive course content for electrician training scenarios. - Configured a web-based community platform using WordPress, BuddyBoss, and Elementor to support digital learning product delivery.
Research center focused on applied AI, digital engineering, and human-AI interaction
- Developed interactive AI-powered child avatar systems for investigative interview training by combining talking-head generation models, game-engine-based avatars, NLP, STT/TTS, and real-time interaction pipelines. - Optimized NeRF-based talking-head generation by integrating Whisper-based audio feature extraction, reducing processing time and improving low-latency avatar interaction. - Built emotionally expressive avatar prototypes using Unreal Engine 5, MetaHuman, NVIDIA Omniverse Audio2Face, and Live Link for audio-driven facial animation. - Designed and evaluated VR/avatar training prototypes using Unity 3D, Oculus Quest 2, and SALSA LipSync Suite, and analyzed user engagement using ANOVA, mixed-effects models, and SEM.
A startup developing conversational AI and avatar-based visual interaction systems
- Developed talking-avatar features for a conversational LLM application, enabling generated text and audio responses to be presented through expressive AI-driven visual agents. - Implemented, tested, and customized open-source GAN, diffusion, and talking-head generation models for avatar generation, facial animation, and visual response generation workflows.
Applying GANs, diffusion models, and NeRF-based methods to build visual AI systems, including talking-head avatars, facial animation pipelines, and generative workflows for medical image analysis.
Developing deep learning and generative AI methods for histopathology image analysis, stain normalization, synthetic data generation, and image segmentation tasks.
Designing interactive AI avatar systems by combining talking-head generation, facial animation, STT/TTS, NLP, Unity/Unreal Engine, MetaHuman, and NVIDIA Audio2Face.
Building LLM-powered applications with document retrieval, vector search, prompt engineering, LangChain, Azure OpenAI, and RAG architectures for knowledge-based assistants.
Creating AI-driven training environments with virtual avatars, VR/3D interaction, conversational agents, and adaptive simulation workflows for professional learning.
Turning research prototypes into user-facing AI products by integrating models, APIs, cloud services, and interactive web platforms into practical workflows.
What I’ve built along the way, each project shaped my journey and taught me something new.

A deep learning project for robust stain normalization in histopathology images using conditional GANs and the Pix2Pix image-to-image translation framework.

A synthetic data generation pipeline for medical image segmentation using SinGAN and single-image training.

A real-time talking portrait synthesis project that uses Whisper for faster audio feature extraction and more responsive AI avatar interactions.

A real-time emotionally expressive child avatar system using Unreal Engine MetaHuman and NVIDIA Audio2Face for training applications.

An AI-driven child interview training platform comparing 2D desktop and 3D VR environments for investigative interview skill development.

An end-to-end computer vision and MLOps project for tomato leaf disease classification, covering PyTorch ResNet18 training, Azure Machine Learning, and Streamlit cloud inference.

An advanced RAG-powered knowledge assistant for reliable document-based question answering with citations, semantic search, and LLM response generation.
Where my experiments turned into papers, from medical images and generative models to AI avatars that can talk back.
P Salehi, SA Sheshkal, V Thambawita, MA Riegler, P Halvorsen
P Salehi, SA Sheshkal, V Thambawita, S Gautam, SS Sabet, D Johansen, ...
P Salehi, SZ Hassan, GA Baugerud, M Powell, MS Johnson, D Johansen, ...
P Salehi, SZ Hassan, M Lammerse, SS Sabet, I Riiser, RK Roed, ...
V Thambawita, P Salehi, SA Sheshkal, SA Hicks, HL Hammer, S Parasa, ...
P Salehi, C Abdolah
Always up for collaborations and interesting projects.