Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

[ICCV 2023 Oral] ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

[arXiv 2025] Generative View Stitching

Repo for the Complete Agentic AI Engineering Course

[ICCV 2025] The official implementation for EgoM2P: Egocentric Multimodal Multitask Pretraining.

Implementation of paper EditCLIP: Representation Learning for Image Editing (ICCV 2025)

Official repository for "MaskControl: Spatio-Temporal Control for Masked Motion Synthesis" ICCV 2025 (Oral & Award Candidate)

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

[ICCV'25] 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

Benchmarking Visual-Inertial SLAM at City Scale (ICCV 2025).

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Towards Unified Image Deblurring using a Mixture-of-Experts Decoder

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Reference PyTorch implementation and models for DINOv3

DeepMVS: Learning Multi-View Stereopsis

Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.

Improving large 3D Reconstruction Models through geometry and texture Refinement

This repository contains a curated collection of 300+ case studies from over 80 companies, detailing practical applications and insights into machine learning (ML) system design. The contents are o…

LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans

GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.

Repo for baseline codes of Digital Twin Catalog project.

[NeurIPS 2025, Spotlight] Rectified Point Flow: Generic Point Cloud Pose Estimation

An open-source AI agent that brings the power of Gemini directly into your terminal.

CVPR'21 "Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance"