[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

A backup of my homework. 矩阵分析

Neovim plugin for GitHub Copilot

Find, Filter, Preview, Pick. All lua, all the time.

ripgrep recursively searches directories for a regex pattern while respecting your gitignore

💥 A curated list of Terminal frameworks, plugins & resources for CLI lovers.

🖥 📊 🕹 🛠 A curated list of command line apps

simple terminal UI for git commands

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

An ML research template with good documentation by Boyuan Chen, an MIT PhD student

✅ Highlight, list and search todo comments in your projects

🌸 A command-line fuzzy finder

Official implementation of HumanVid, NeurIPS D&B Track 2024

world modeling challenge for humanoid robots

Utility functions for weights and biases (wandb).

Compute FID scores with PyTorch.

A Slurm dashboard for the terminal.

Code for "Temporal Difference Learning for Model Predictive Control"

Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning

A Survey of Embodied Learning for Object-Centric Robotic Manipulation

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Unified framework for robot learning built on NVIDIA Isaac Sim

AI Q&A Search Engine ➡️ 基于LangChain和SearXNG打造的开源AI搜索引擎

[NeurIPS 2024] Code release for "Segment Anything without Supervision"