arXiv Machine Learning July 8, 2026 By Lorenzo Tarricone, Helen E. Eisenach, Aiko Muraishi, Charlotte M. Deane

Design-CP: Context Parallelism for Design of Protein Nanoparticles

Read the original on arXiv Machine Learning →

arXiv:2607. 05439v1 Announce Type: new Abstract: Many all-atom generative protein models can in principle design large multimeric complexes by jointly modelling all chains, but their quadratic token- and atom-pair representations quickly exceed single-GPU memory as the number of chains and residues modelled grows.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

22h ago

Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design

arXiv:2608. 17381v1 Announce Type: cross Abstract: Biomolecular design underpins applications from molecular recognition to therapeutics and synthetic biology, yet de novo interaction design remains challenging-especially for DNA/RNA, underexplored non-protein modalities with scarce, heterogeneous complex data and sharper geometric and chemical constraints.

By Xuefeng Liu, Mingxuan Cao, Xiao Luo, Songhao Jiang, Tobin Sosnick, Jinbo Xu, Louis Maher, Rick Stevens

fine-tuning safety

arXiv AI

Aug 10

Scalable High-Fidelity Macromolecular Docking for GPU-Accelerated Supercomputers

arXiv:2608. 07078v1 Announce Type: cross Abstract: Flexible macromolecular docking offers high-fidelity predictions of biomolecular interactions, but remains prohibitively expensive at scale.

By Xiangyu Meng, Peng Chen, Mingzhen Li, Jianmin Wang, Sen Wang, Guangming Tan, Weile Jia, Mohamed Wahib, Tao Luo, Xun Wang

agents

arXiv Machine Learning

Jun 16

MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs

arXiv:2506. 20686v2 Announce Type: replace-cross Abstract: Recent advances in biomolecular modeling have been catalyzed by models such as AlphaFold3 (AF3), which introduce science-informed changes to the transformer architecture.

By Hoa La, Ahan Gupta, Alex Morehead, Jianlin Cheng, Minjia Zhang

llms

arXiv Machine Learning

Jul 23

Boltzmann-Expected Molecular Design with Decoupled Annealing Flows

arXiv:2607. 19519v1 Announce Type: cross Abstract: Most 3D properties relevant to molecular design, including free energies and shape descriptors, are $\textit{expectations}$ over the Boltzmann distribution over 3D configurations of a molecular graph.

By Selma Moqvist, Richard Beckmann, Ross Irwin, Roc\'io Mercado, Simon Olsson

arXiv Machine Learning

Jun 25

Scalable Peptide Design via Memory-Efficient Equivariant Transformer

arXiv:2606. 25006v1 Announce Type: new Abstract: Target-specific peptide design requires sequence and structure co-design under full atom geometric constraints.

By Rui Jiao, Xiangzhe Kong, Yinjun Jia, Yijia Zhang, Ziyi Yang, Yang Liu, Jianzhu Ma

llms diffusion

arXiv Machine Learning

Jun 8

Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport

arXiv:2606. 07239v1 Announce Type: new Abstract: The success of generative molecular design hinges on a model's steerability toward high-reward samples.

By Malte Franke, Stefan P. Schmid, Zarko Ivkovic, Kjell Jorner, Andreas Krause

diffusion benchmarks

Related stories

Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design

Scalable High-Fidelity Macromolecular Docking for GPU-Accelerated Supercomputers

MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs

Boltzmann-Expected Molecular Design with Decoupled Annealing Flows

Scalable Peptide Design via Memory-Efficient Equivariant Transformer

Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport