The field of protein design and generation is rapidly advancing, with a focus on developing innovative methods for creating proteins with desired functionalities. Recent research has explored the use of generative models, flow matching, and integer linear programming to design protein sequences and predict their properties. These approaches have shown promise in improving the efficiency and accuracy of protein design, particularly in the context of multi-chain proteins and protein complexes. Notably, the integration of atom-level information and the use of compressed protein language model embeddings have enabled the development of fast and effective protein sequence design frameworks. Overall, the field is moving towards more sophisticated and versatile methods for protein design and generation, with potential applications in biotechnology and medicine. Noteworthy papers include: Compositional Flows for 3D Molecule and Synthesis Pathway Co-design, which introduces a novel framework for generating compositional objects with continuous features. ProtFlow, a fast flow matching-based protein sequence design framework that operates on compressed protein language model embeddings. An All-Atom Generative Model for Designing Protein Complexes, which presents a model specifically designed for modeling multi-chain proteins and designing protein complexes with binding capabilities from scratch.