Skip to content
View subh-775's full-sized avatar
🦝
SOTA Diffusion models
🦝
SOTA Diffusion models
10 followers · 7 following

Achievements

Achievement: YOLOAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: Pull Shark

Block or report subh-775

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
subh-775/README.md

Subhansh Malviya

Vision + Perception + Interpretation

Summary

Hi there, I am Subhansh Malviya I am an Applied Computer Vision Researcher. I like to build prototypes using existing methods which solves real-problems, other than quantizating or finetuning a model. I like to focus on mathematical intution behind existing principles, like how model architectures are made, loss functions, statistics and benchmarks..

Core Competencies

  • Research Domain: Computer Vision
  • Frameworks: PyTorch, Transformers, LangChain
  • Data & MLOps: Pandas, NumPy, Matplotlib, Docker, FAISS, TensorBoard, WandB
  • Languages & Tools: Python, SQL, Git, Linux, Jupyter
  • Cloud & Deployment: AWS, Vercel, Render, HF-spaces

Current..

  • CLIP vs Perception Encoder combining (Vision+language) [D Bolya. Research Scientist (FAIR) at meta.]
  • Accuracy-latency pareto curve in real-time detectors....
  • Open-Vocabulary Detectors..

Connect with me:

Pinned Loading

  1. Artistic-Prompt-AI Artistic-Prompt-AI Public

    A machine learning model that generates creative, poster-style images from text prompts, complete with unstructured, visually striking text overlays. Ideal for crafting visuals with custom captions…

    Jupyter Notebook 1

  2. ControlNet ControlNet Public

    Forked from lllyasviel/ControlNet

    Let us control diffusion models!

    Python

  3. facebookresearch/sam2 facebookresearch/sam2 Public

    The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

    Jupyter Notebook 17.8k 2.2k

  4. Stable-X/StableNormal Stable-X/StableNormal Public

    [SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

    Python 729 35

  5. GeoWizard GeoWizard Public

    Forked from fuxiao0719/GeoWizard

    [ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

    Python

  6. google/nerfies google/nerfies Public

    This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

    Python 1.9k 264