# Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute

arXiv: https://arxiv.org/abs/2603.27950 · HTML: https://mlsanity.com/paper/2603.27950/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 79 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [Swallowing the Bitter Pill: Simplified Scalable Conformer Generation](https://mlsanity.com/paper/2311.17932/) (2023)
- [A Fourier Space Perspective on Diffusion Models](https://mlsanity.com/paper/2505.11278/) (2025)
- [Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2](https://mlsanity.com/paper/2405.15489/) (2024)
- [Test-Time Scaling of Diffusion Models via Noise Trajectory Search](https://mlsanity.com/paper/2506.03164/) (2025)
- [FLOWR.root: A flow matching based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction](https://mlsanity.com/paper/2510.02578/) (2025)
- [Latent Beam Diffusion Models for Generating Visual Sequences](https://mlsanity.com/paper/2503.20429/) (2025)

## Built on by (most cited first, 15 of 15)

- [Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching](https://mlsanity.com/paper/2606.03199/) (2026)
- [Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching](https://mlsanity.com/paper/2605.11547/) (2026)
- [Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics](https://mlsanity.com/paper/2604.25244/) (2026)
- [AlloGen: Conformation-Selective Binder Generation with Differential State Scoring](https://mlsanity.com/paper/2606.05474/) (2026)
- [Few-step Cofolding with All-Atom Flow Maps](https://mlsanity.com/paper/2606.08375/) (2026)
- [Emyx: Fast and efficient all-atom protein generation](https://mlsanity.com/paper/2606.19377/) (2026)
- [Folding, Reasoning, and Scaling with Open-source Drug Discovery Engine](https://mlsanity.com/paper/2607.03787/) (2026)
- [SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign](https://mlsanity.com/paper/2609.03377/) (2026)
- [Ligand-Conditioned Discrete Diffusion for Protein Sequence-Structure Co-Design](https://mlsanity.com/paper/2605.27413/) (2026)
- [Design-CP: Context Parallelism for Design of Protein Nanoparticles](https://mlsanity.com/paper/2607.05439/) (2026)
- [Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling](https://mlsanity.com/paper/2607.23518/) (2026)
- [CODesign: Consistency from Data to Trajectory in All-Atom Protein Binder Co-Design](https://mlsanity.com/paper/2610.01773/) (2026)
- [Inference-Time Steering Across Scaffolds and Epitopes for Sample-Efficient De Novo Nanobody Design](https://mlsanity.com/paper/2610.13844/) (2026)
- [Joint Discrete and SE(3) Diffusion for Protein Interface Design](https://mlsanity.com/paper/2610.14699/) (2026)
- [InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design](https://mlsanity.com/paper/2610.19592/) (2026)

## Abstract (arXiv)

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.