Skip to content
View miheer-smk's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report miheer-smk

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
miheer-smk/README.md

Miheer Satish Kulkarni

AI · Computer Vision · Physics-Informed ML
Building models that reason from first principles instead of memorizing patterns.

Followers Profile views Focus


About

I'm an AI/Computer Vision researcher at IIIT Nagpur, working at the intersection of physics, cognition, and machine learning. My projects tend to share one thread: grounding models in the actual constraints of the physical world — sensor noise, light transport, quantum structure — rather than treating them as pattern-matchers over pixels.

  • 🔬 Researching physics-anchored deepfake detection and mechanistic interpretability
  • 🧬 Built an agentic AI tutoring platform with hierarchical memory and epistemic-state modeling
  • 📷 Deep interest in sensor physics, noise modeling, and interpretable computer vision
  • 🛠️ Bias toward building from scratch — no pretrained shortcuts when the goal is understanding

Featured Work

Project What it does Highlight Stack
👻 Phantom Lens Physics-anchored deepfake detection (PRISM V3) — validates whether video obeys real-world physics across 50 features / 4 pillars: PRNU sensor noise, light transport, compression forensics, rPPG cardiac signals. AUC 0.97 in-distribution · 92% fake recall zero-shot cross-dataset PyTorch · LightGBM · MediaPipe · SHAP
🔬 Quantum-Structure SAE Mechanistic interpretability: do classical transformers trained on quantum data (1D TFIM) encode quantum observables? Linear probing, TopK SAEs, activation patching, 5-part control battery. Order parameter decodable at partial corr. 0.71 — but not load-bearing PyTorch · PennyLane · scikit-learn
🛡️ AEGIS Agentic tutoring platform that thinks between sessions: 6 teaching agents, 4-layer memory stack, Ebbinghaus forgetting curve + SM-2, Theory-of-Mind modeling, always-on background cognition. 6–10× memory compression · <5ms predictive pipeline Next.js · TypeScript · Claude · D3.js
🔭 PhysDenoiser Image denoiser trained from scratch on physically realistic Poisson–Gaussian noise. Residual CNN, mixed L1+SSIM loss. No pretrained weights, no APIs. 22.45 dB val PSNR · 30K-param CPU variant PyTorch · NumPy · OpenCV

Tech Stack

Tech stack

Languages  Python · TypeScript · C++ ML / CV  PyTorch · OpenCV · scikit-learn · LightGBM · MediaPipe · NumPy · SciPy · PennyLane Interpretability  Sparse Autoencoders · Linear Probing · Activation Patching · SHAP Web / Systems  Next.js · React · Tailwind · Node.js · SQLite · Docker · Vercel


GitHub Stats

GitHub stats

Top languages by repo Most-committed languages


Connect

LinkedIn Email GitHub

"Build models that reason from first principles — one physically-grounded system at a time."

Popular repositories Loading

  1. aegis-ai-learning aegis-ai-learning Public

    AEGIS — Agentic AI Learning Platform with Epistemic State Modeling, Ebbinghaus Forgetting Curve, and Cognitive DNA Adaptation.

    TypeScript 3

  2. OpenMythos OpenMythos Public

    Forked from kyegomez/OpenMythos

    A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

    Python 1

  3. phantom-lens phantom-lens Public

    Physics-Anchored Deepfake Detection Framework

    Python

  4. phys-denoiser phys-denoiser Public

    Physics-informed image denoiser built from scratch — Poisson-Gaussian noise modeling, residual CNN, no pretrained weights or APIs

    Python

  5. miheer-smk miheer-smk Public

  6. quantum-structure-sae quantum-structure-sae Public

    Mechanistic interpretability of classical neural networks trained on quantum data — using sparse autoencoders to detect quantum structure in classical representations.

    Python