Explore Projects
Discover 79 open source projects
Showing 1-20 of 79 projects
haotian-liu/LLaVA
LLaVA is a visual instruction tuning framework for large language and vision models, enabling GPT-4 level capabilities.
SWE-agent/SWE-agent
SWE-agent is an AI-powered tool that automatically fixes GitHub issues using large language models.
sczhou/CodeFormer
A PyTorch-based library for robust and high-quality blind face restoration using a codebook lookup transformer.
THU-MIG/yolov10
An open-source real-time object detection library powered by the YOLOv10 neural network model.
FoundationVision/VAR
An ultra-simple, state-of-the-art codebase for autoregressive image generation using advanced AI models.
DepthAnything/Depth-Anything-V2
A highly capable foundation model for monocular depth estimation, a key component in computer vision.
HVision-NKU/StoryDiffusion
An AI-powered story generation tool for developers interested in vibe coding and creative AI applications.
princeton-nlp/tree-of-thought-llm
A research paper that introduces a novel approach for using large language models to solve complex problems through a tree-based reasoning process.
UX-Decoder/Segment-Everything-Everywhere-All-At-Once
Official implementation of a paper on segmentation models for computer vision tasks.
stanford-futuredata/ColBERT
State-of-the-art neural search engine
OSU-NLP-Group/HippoRAG
HippoRAG is a novel RAG framework that enables LLMs to continuously integrate knowledge across external documents.
guandeh17/Self-Forcing
Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion
Pointcept/Pointcept
Pointcept is a codebase for point cloud perception research, featuring the latest works on 3D computer vision.
MeiGen-AI/MultiTalk
Multimodal conversational video generation powered by AI, enabling new vibe-coder collaboration experiences.
sunsmarterjie/yolov12
Real-time object detector using YOLOv12 with attention-centric architecture
xlang-ai/OSWorld
A benchmark for multimodal AI agents to tackle open-ended tasks in real computer environments.
VITA-MLLM/VITA
A powerful multimodal AI model for real-time vision and speech interaction, built for developers who work with AI tools.
thuml/Autoformer
Autoformer: A deep learning model for long-term time series forecasting, focused on developers building with AI tools.
OmniSVG/OmniSVG
An end-to-end multimodal SVG generator that leverages pre-trained Vision-Language Models to create complex and detailed SVGs.
wgsxm/PartCrafter
PartCrafter is a 3D mesh generation tool that uses compositional latent diffusion transformers to create structured 3D objects.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.