-
Indian Institute of Technology, Madras
- India
- https://www.linkedin.com/in/jsk1995
Highlights
Stars
Real-time face/body 3D reconstruction on iOS using TrueDepth camera
Added TrueDepth support to the infiniTAM ios app
Download market data from Yahoo! Finance's API
Official inference repo for FLUX.2 models
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
Reference PyTorch implementation and models for DINOv3
[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
A Modular Framework for 3D Generation and Beyond [WIP]
Algorithms and Publications on 3D Object Tracking
A high-throughput and memory-efficient inference and serving engine for LLMs
Simulation platform for general-purpose robotics & embodied AI learning.
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
[NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
[ACM MM 2024] This is the official code for "AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding"
[INTERSPEECH'24] Official repository for "MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset"
[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
Code repository for the paper "On the Benefits of 3D Pose and Tracking for Human Action Recognition", (CVPR 2023)
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
A work list of recent human video generation method. This repository focus on half/full body human video generation method, The Nerf, Gaussian splashing, Motion Pose, and talking head/Portrait is n…


