RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features (CVPR 2021)

MindManager AI Integration on Windows and macOS

Improving genome bins through the combination of different binning programs

Refinement, finetuning, and deployment of RT-DETRv2.

Python-based system that automatically applies refinement techniques to LLM and reduces hallucination.

Built framework for Image dehazing for autonomous/electric vehicles driving in inclement weather conditions using deep learning Created a dehazing interface using Stream Lit which takes a foggy image as an input and gives the clear image as an output .Took an existing dataset, cleaned, and manipulated using Python and Deployed on website through…

Pipeline and GUI for cryoEM model refinement using Rosetta and Phenix

An experiment in synthesis of C code from a functional language.

python class utility of 2D auto-refining grid to solve thermodynamic equilibrium problems

Relaxed multi-levelset segmentation package, with tomographically consistent refinement.

Official implementation of Neural Mesh Refinement (NMR): a robust mesh refinement method that learns rich structural priors during training and then adaptively applies the priors during inference to refine coarse shapes to finer ones based on their geometry.

Repo for the COLING 2025 paper "What's Wrong? Refining Meeting Summaries with LLM Feedba"

Pixel-wise segmentation on VOC2012 dataset using pytorch.

Tools for mesh refinement and manipulation

This project uses machine learning to enhance CAPTCHA systems by generating robust challenges and validating user responses. It combines a CNN model for CAPTCHA recognition, adversarial techniques to deter bots, and a customizable Streamlit web interface for improved security and user experience.