Selected archive
Project index / 24 records
Things I've built.
Open-source experiments and production toolkits spanning document intelligence, explainable AI, computer vision, and autonomous robotics.
- 01LLM interpretability
Role Confusion Reproduction
Reproduction study of the role confusion paper: linear probes predict each token's chat role from model activations across six open LLMs, testing how much role recognition depends on chat-template tags.
- #AI
- #LLMs
- #Research
nnrc-viewer-eight.vercel.app - 02Document AI
DocDjinn
General-purpose framework built on vision-language models and diffusion-based handwriting models for controllable generation of full-page synthetic documents, along with their annotations, to train models across diverse downstream document understanding tasks
- #AI
- #Research
arxiv.org - 03Machine learning
AtriaX
Web-based document AI platform built on Atria for dataset and model management, training, evaluation, and explanation visualization
- #AI
- #Development
- #MLOps
atriaml.github.io - 04Explainable AI
TorchXAI
Explainable AI toolkit with 20+ explainability metrics and 11+ multi-output explainers, enabling fast, scalable evaluation of interpretability in multimodal deep learning models
- #AI
- #Development
- #Research
atriaml.github.io - 05Explainable AI
DocVCE
Explainability method for generating visual counterfactuals via guided latent diffusion to interpret the decisions of document classifiers
- #AI
- #Research
doi.org - 06ai
DP-DocLDM
Differentially private document image dataset generation using layout-conditioned latent diffusion models
- #AI
- #Research
doi.org - 07Document AI
DocPrivacy
Privacy-preserving multimodal document information extraction through differential privacy, federated learning, and encrypted inference
- #AI
- #Research
doi.org - 08Document AI
DocXClassifier
Augments CNN-based classifiers with pyramid-attention modules to introduce inherent interpretability
- #AI
- #Research
github.com - 09Computer vision
ColDBin
An approach to document image binarization through cold diffusion
- #AI
- #Computer vision
- #Research
github.com - 10Machine learning
DocAL
A complete active-learning toolkit for deep learning classification tasks
- #AI
- #Development
github.com - 11Document AI
DocRobustness
A toolkit for generating and evaluating corruption-robustness benchmarks for document images
- #AI
- #Computer vision
- #Research
github.com - 12Explainable AI
DocXAI
A toolkit for explainable AI in document image classification
- #AI
- #Research
github.com - 13Edge AI
DeepStream Media
An NVIDIA DeepStream pipeline for real-time detection and tracking of individuals in news media
- #AI
- #Development
- #Computer vision
github.com - 14Edge AI
DeepStream Retail App
An NVIDIA DeepStream pipeline for real-time traffic tracking and analytics in retail stores
- #AI
- #Development
- #Computer vision
gist.github.com - 15Robotics
Generalized Whole Body Motion Architecture for a Humanoid Robot NAO
Master's Thesis
A generalized whole-body motion architecture for NAO humanoid robots, built on task-based inverse kinematics, Newton-Euler inverse dynamics, and dynamic balance control, demonstrated through real-time omni-directional walking, kicking, and targeted diving motions
- #Robotics
Archive record - 16Robotics
Dynamically Stable and Impact-Controlled Humanoid Kick
Bachelor's Thesis
A momentum-control-based omni-directional kick engine for the NAO humanoid robot, achieving approximately 90% average kicking accuracy
- #Robotics
Archive record - 17Robotics
Mavros / MoveIt
Integrates MoveIt motion planning with MAVROS-based aerial robots in ROS
- #Robotics
- #Development
github.com - 18Robotics
RosGym
Integrates Gym with ROS to train reinforcement-learning agents in ROS and AirSim environments
- #Robotics
- #AI
- #Development
github.com - 19Robotics
Irl2DRos
A ROS navigation package for 2D mobile robots, focused on the Pioneer 3-AT platform
- #Robotics
- #Development
github.com - 20Robotics
NAO Autonomous Robotics Stack · RoboCup SPL
Robotics stack integrating vision, motion planning, state-estimation/localization, and multi-robot coordination for fully autonomous RoboCup SPL gameplay
- #Robotics
- #Development
github.com - 21Robotics
UAV Exploration
Frontier-based exploration for navigating unknown environments and generating octomaps
- #Robotics
- #Development
github.com - 22Visual SLAM
ORB-SLAM
A custom ROS implementation of ORB-SLAM for monocular and RGB-D cameras with bundle adjustment
- #Robotics
- #Computer vision
- #Development
github.com - 23Robotics
VFH3D+
An octomap-based VFH+ algorithm in 3D for local planning of UAVs and other robots operating in 3D
- #Robotics
- #Development
github.com - 24Robotics
Fusion of IMU and Vision Observations for State Estimation of a Quadrotor
A ROS and Gazebo case study fusing monocular optical flow with IMU measurements for quadrotor position and orientation estimation
- #Robotics
- #Computer vision
Archive record
End of archive