Ansh Mittal | Personal Website

Ansh Mittal

5+ yrs of ML experience bridging 3D Computer Vision and LLM optimization, spanning foundational research to enterprise production. Proven track record of shipping optimized spatial pipelines and architecting large-scale agentic AI systems. Skilled in translating cutting-edge prototypes (NeRFs, Gaussian Splats) and fine-tuned Language modelsz into scalable, production-ready workflows for complex computing challenges.

A Little About Me

As a professional, my main aim is to understand how scientific processes are responsible for producing the interactions and measurements observed in the experiments and projects I work on. I use a combination of approaches and technologies for my studies. Learn more about my research and areas of study below.

Contact Me

Ongoing Projects

January 17, 2025

CUDAx365 Animation Set

Black Hole 3D Flow

CUDAx365 black-hole simulations and Neural Radiance Field experiments for dynamic flow analysis, MHD graph kernels, and approximation studies.

3D hot/cold stellar flowMHD CUDA graph kernel combinedMHD CUDA approximations

January 2026

Stay tuned

Cyber Attack Signal Simulation

I will be adding Wireshark PCAP signal usage and the electromagnetic spectrum in enclosed environments to simulate cyber attacks.

Wireshark PCAP signalsEM spectrum in enclosed environmentsCyber-attack simulation videos coming next

3D Medical Imaging

Volumetric U-Net

3D CT Scan Segmentation

A U-Net-style segmentation pipeline adapted from 2D slices to volumetric CT data by using 3D feature blocks, skip-connected encoder-decoder paths, and spatial context across neighboring slices.

3D CT volumesEncoder-decoder segmentationSlice-to-slice context

Fundus CAD Research

EfficientNet B1

EfficientNet Fundus Classification

Fundus disease classification across 40 abnormality labels using fine-tuned pretrained CNNs. EfficientNet B1 was the strongest single-model choice, with high precision/recall on the reported split and a practical path toward computer-aided retinal screening.

40 fundus labelsFine-tuned CNNsCAD for retinal screening

World Models

VAE + MDN-RNN + CMA-ES

World Model Implementation

Implementation of the World Models agent pattern: a CNN-VAE compresses image frames, an MDN-RNN predicts future latent states, and CMA-ES optimizes a compact controller over the learned latent memory.

Latent visual modelMixture-density memoryEvolutionary controller

AR + AI Insurance

AR INSURIM

AR Insurance Prototype

An AR insurance prototype for inspecting policy objects and claim context in-place. The same flow can evolve with AI-assisted damage detection, guided evidence capture, and real-time claim triage.

AR inspectionAI claim triageGuided evidence capture

Loading ...