1. [Publications](/index.php/publications)
2. Proteina-Complexa: Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute
 
 # Proteina-Complexa: Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 Protein interaction modeling is central to protein design, which has been transformed by machine learning with applications in drug discovery and beyond. In this landscape, structure-based de novo binder design is cast as either conditional generative modeling or sequence optimization via structure predictors ("hallucination"). We argue that this is a false dichotomy and propose Proteina-Complexa, a novel fully atomistic binder generation method unifying both paradigms. We extend recent flow-based latent protein generation architectures and leverage the domain-domain interactions of monomeric computationally predicted protein structures to construct Teddymer, a new large-scale dataset of synthetic binder-target pairs for pretraining. Combined with high-quality experimental multimers, this enables training a strong base model. We then perform inference-time optimization with this generative prior, unifying the strengths of previously distinct generative and hallucination methods. Proteina-Complexa sets a new state of the art in computational binder design benchmarks: it delivers markedly higher in-silico success rates than existing generative approaches, and our novel test-time optimization strategies greatly outperform previous hallucination methods under normalized compute budgets. We also demonstrate interface hydrogen bond optimization, fold class-guided binder generation, and extensions to small molecule targets and enzyme design tasks, again surpassing prior methods. Code, models and new data will be publicly released.



 ## Authors



[Kieran Didi](/index.php/person/kieran-didi)

Zuobai Zhang (NVIDIA, Mila - Quebec AI Institute, Universite de Montreal)

Guoqing Zhou (NVIDIA)

Danny Reidenbach (NVIDIA)

Zhonglin Cao (NVIDIA)

Sooyoung Cha (Seoul National University)

[Tomas Geffner](/index.php/person/tomas-geffner)

Christian Dallago (NVIDIA)

Jian Tang (Mila - Quebec AI Institute, HEC Montreal, CIFAR AI Chair)

Michael M. Bronstein (University of Oxford, AITHYRA)

Martin Steinegger (Seoul National University)

Emine Kucukbenli (NVIDIA)

[Arash Vahdat](/index.php/person/arash-vahdat)

[Karsten Kreis](/index.php/person/karsten-kreis)

 

 

 ## Publication Date



Monday, January 26, 2026

 

 ## Published in



[International Conference on Learning Representations (ICLR) 2026 (Oral)](https://arxiv.org/abs/2603.27950)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence)

[Generative AI](/index.php/research-area/generative-ai)

 

 

 ## External Links



[Project Website](https://research.nvidia.com/labs/genair/proteina-complexa/)