cv

Education, experience, and technical skills. A PDF version is linked below.

Education

B.S., Electrical Engineering and Computer Science — Indian Institute of Science Education and Research (IISER) Bhopal September 2023 – May 2027

Experience

Member of Technical Staff, Pretraining TeamOverworld October 2025 – Present

  • Training foundational interactive video models.
  • Scaling up and optimizing data and inference pipelines for custom and pre-trained open-source video diffusion models.

Research Intern — Vision and AI Lab, Indian Institute of Science (IISc) December 2024 – August 2025

  • Created a dataset for object relighting using the BlenderProc API with procedural camera poses and environment lighting maps.
  • Conducted literature surveys of ICCV 2026 and CVPR 2025 papers on video relighting and video diffusion models.
  • Performed efficient LoRA fine-tuning of the WanVideo 1.3B model on a custom dataset using Diffusion-Pipe, with inference via Hugging Face Diffusers.
  • Ran and compared state-of-the-art video diffusion models (Hunyuan, Mochi-1, CogVideoX) on server-grade hardware using Hugging Face Diffusers, ComfyUI, and xDiT for multi-GPU inference.
  • Internship report

Publications

  • Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware — Overworld (preprint, 2026). Project page
  • COMBAT: Conditional World Models for Behavioral Agent Training — 1st RIWM Workshop, ICCV 2025 (non-archival).

Technical Skills

  • Languages: C++, C, Java, GLSL, Python, MATLAB
  • Developer Tools: Visual Studio, Git, GitHub, Linux
  • Libraries & APIs: Hugging Face Diffusers, PyTorch, OpenGL, Dear ImGui, NumPy, Matplotlib
  • Areas of Interest: Computer Vision, GenAI, Diffusion Models, Transformers, Graphics Programming, Simulation