The field of protein research is experiencing significant advancements in modeling and design, with a focus on developing innovative methods to explore the conformational space of proteins and design novel protein sequences. Recent developments have led to the creation of autoregressive models that can simultaneously learn protein conformation and dynamics, enabling the efficient exploration of protein structures and functions. Additionally, iterative frameworks for generative backmapping have improved the accuracy and efficiency of reconstructing protein structures from coarse-grained representations. Active learning approaches have also been proposed to design protein sequences with high fitness and novelty, while preserving biological plausibility. Furthermore, novel diffusion language models have been introduced to generate combinatorial functional proteins, integrating multiple constraints and modalities. Notable papers include: ProSpero, which enables exploration beyond wild-type neighborhoods while preserving biological plausibility. CFP-Gen, which facilitates the de novo protein design by integrating multimodal conditions with functional, sequence, and structural constraints.