#
Starred repositories
[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding
Packing irregular objects with deep reinforcement learning.
CoPart (ICCV 2025): A part-based 3D generation framework & the first large-scale part-level 3D dataset.
从无名小卒到大模型（LLM）大英雄~ 欢迎关注后续！！！
Collection of papers using LLaMA as backbone model
An open source implementation of CLIP.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Official implementation of Diffusion Policy Policy Optimization, arxiv 2024
LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
A 3DGS framework for omni urban scene reconstruction and simulation.
DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
(ICCV 2025) UAVScenes: A Multi-Modal Dataset for UAVs
PyTorch 1.0 implementation of the approximate Earth Mover's Distance
An open source library that integrates various point cloud registration algorithms
Repository for running the VGGT model in PyTorch
[Accepted by ICCV2025] Official code of the paper "From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision"
The code of paper "Structure–Aware Surface Reconstruction via Primitive Assembly" (ICCV2023)
A curated list of reinforcement learning with human feedback resources (continually updated)
ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning
12 Lessons to Get Started Building AI Agents
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).