3 Repos
Modules that iteratively improve outputs based on feedback and reward functions.
Distinguishing note: Focuses on iterative refinement, distinct from one-shot generation.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Refinement Modules. Refine with filters or upvote what's useful.
DSPy is a declarative programming framework designed for building complex language model applications. It treats model interactions as modular, composable programs, allowing developers to define task logic through typed class schemas rather than relying on manually written prompts. By organizing workflows into hierarchical, reusable Python objects, the framework enables the construction of sophisticated AI systems that manage state and execution flow independently. The framework distinguishes itself through an automated optimization engine that iteratively refines prompt instructions and few-
Iteratively refines module outputs by running them multiple times against reward functions.
AlphaFold is a deep learning biology tool and structural bioinformatic pipeline designed to predict the three-dimensional shapes of proteins from their amino acid sequences. It functions as a machine learning system capable of generating 3D molecular models for both monomeric proteins and multimeric protein complexes, including homomers and heteromers. The system incorporates evolutionary information through multiple sequence alignment to identify physical proximity between residues. It utilizes a neural network architecture featuring spatial attention mechanisms and iterative refinement to d
Provides a module that recursively refines 3D atomic coordinates through iterative neural network passes.
PlugNPlay-Modules is a collection of reusable PyTorch computer vision modules and deep learning architectural components. It provides a library of standardized building blocks for constructing neural networks, focusing on attention mechanisms, signal processing layers, and feature fusion modules. The project is distinguished by its extensive variety of attention primitives, covering spatial, channel, and temporal weighting, as well as specialized variants like deformable, frequency-enhanced, and linear-complexity attention. It also implements advanced signal processing tools within the neural
Ships sequences of self-modulation and partial convolution blocks using residual connections to refine input features.