NOVA3R implements a non-pixel-aligned visual transformer for amodal 3D reconstruction from unposed multi-view images, recovering occluded geometry with physical plausibility.
OmniStream uses a multi-frame transformer to process continuous video streams with patch-level temporal indexing, supporting downstream vision-language-action tasks.
This repo provides annotated PyTorch implementations of major deep learning papers with side-by-side explanations, aiding understanding and prototyping.
LlamaFactory offers a modular Python framework for fine-tuning 100+ LLMs with diverse algorithms and optimizations, including LoRA, QLoRA, and reinforcement learning.
ComfyUI offers a graph/node interface for building complex diffusion model workflows offline, blending modularity with flexibility for AI practitioners.
Explore PyTorch’s unique tape-based autograd and dynamic neural networks architecture that enables flexible model development and efficient GPU-accelerated tensor computation.
YOLOv5 by Ultralytics offers an accessible, fast, and accurate PyTorch-based computer vision toolkit for object detection, segmentation, and classification. Explore its architecture, strengths, and quickstart usage.
Keras 3 introduces a multi-backend architecture supporting JAX, TensorFlow, PyTorch, and OpenVINO, enabling flexible, accelerated deep learning model development with up to 350% speedups.
