AI Researcher and Engineer
taneemishere@gmail.com

CV

Taneem Ullah Jan

I work at the intersection of multimodal learning, 3D human modeling, and generative AI to advance neural avatars, virtual humans, and replicate aspects of the human brain. I serve as an AI Researcher at VOLV AI, where I direct the machine learning team in exploring innovative solutions in 3D computer vision for virtual try-on and digital human synthesis. Previously, I worked as a Research AI Engineer at BHuman AI, leading research and development for their core generative AI products.

Research Work

Some projects are highlighted.

tldr: An embedding-driven approach combines audio encoders with multimodal projectors to enable direct speech-to-text processing, achieving significant performance while training minimal parameters through block optimization.

tldr: An interactive 3D body modeling system that allows real-time manipulation of human body shapes through intuitive measurement sliders with immediate visual feedback in a fully navigable 3D environment.

tldr: VMVLM enhances vision-language models by using dual visual pathways, combining Q-Former queries with direct ViT feature injection for improved multimodal instruction following.

tldr: A self-improving AI system that uses LLMs and evolutionary algorithms to autonomously enhance code across multiple quality dimensions.

tldr: A unified framework for 3D virtual try-on that transforms simple 2D images into realistic 3D representations, by efficiently integrating clothing with the human body in a pose-adaptive manner.

tldr: A two-stage unified audio-driven talking face generation framework, which can render high-fidelity, lip-synchronized videos with improved inference speed.

tldr: Current image inpainting techniques are too heavy; this paper introduces a Row-wise Flat Pixel LSTM, a small hybrid model for the efficient and high-quality restoration of small images.

tldr: A robust and efficient talking face generation model with highly accurate lip synchronization and full facial expressiveness with more extended audio and high-quality video resolutions.

tldr: An unsupervised one-shot talking head video generation model using neural rendering and motion transfer techniques with non-linear transformation to animate static images.

tldr: Innovative face-swapping model that preserves the source identity features accurately while seamlessly adapting target attributes applicable to images and videos.

tldr: An accurate deep learning model converting GUI mockups into HTML code, streamlining web development for non-programmers.

Thanks to Jon Barron for this template.