Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling

Hengyuan Cao, Shizhuo Cheng, Mingxuan Liu, Weicheng Huang, Yunhong Lu, Cai Chenxi, Yan Zhang, Min Zhang
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:11120-11140, 2026.

Abstract

The rapid evolution of generative models has unlocked new potentials in protein binder design, a pivotal task in structural biology, by facilitating end-to-end generation via joint sequence-structure modeling or hallucination. However, existing approaches are predominantly implemented under a single-target, single-state assumption, limiting their ability to model multi-target or multi-state interactions required for advanced function-oriented protein design. Here, we introduce Chamaileon, which unifies multi-target and multi-state binder design by formulating the problem as cross-context binding landscape modeling. The framework is underpinned by a training paradigm termed In-Context Complex Co-Design (I3CD) for context-aware sequence-structure co-modeling. During inference, we employ Mixture-of-Paths Sampling (MoPS), a scalable strategy that optimizes a single sequence across contexts while alleviating the scarcity of high-quality multi-conformational paired data. Extensive evaluation on our newly constructed benchmark, CROSS, demonstrates that Chamaileon effectively generates sequences adaptable to diverse conformational landscapes and multi-target requirements.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-cao26c, title = {Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling}, author = {Cao, Hengyuan and Cheng, Shizhuo and Liu, Mingxuan and Huang, Weicheng and Lu, Yunhong and Chenxi, Cai and Zhang, Yan and Zhang, Min}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {11120--11140}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/cao26c/cao26c.pdf}, url = {https://proceedings.mlr.press/v306/cao26c.html}, abstract = {The rapid evolution of generative models has unlocked new potentials in protein binder design, a pivotal task in structural biology, by facilitating end-to-end generation via joint sequence-structure modeling or hallucination. However, existing approaches are predominantly implemented under a single-target, single-state assumption, limiting their ability to model multi-target or multi-state interactions required for advanced function-oriented protein design. Here, we introduce Chamaileon, which unifies multi-target and multi-state binder design by formulating the problem as cross-context binding landscape modeling. The framework is underpinned by a training paradigm termed In-Context Complex Co-Design (I3CD) for context-aware sequence-structure co-modeling. During inference, we employ Mixture-of-Paths Sampling (MoPS), a scalable strategy that optimizes a single sequence across contexts while alleviating the scarcity of high-quality multi-conformational paired data. Extensive evaluation on our newly constructed benchmark, CROSS, demonstrates that Chamaileon effectively generates sequences adaptable to diverse conformational landscapes and multi-target requirements.} }
Endnote
%0 Conference Paper %T Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling %A Hengyuan Cao %A Shizhuo Cheng %A Mingxuan Liu %A Weicheng Huang %A Yunhong Lu %A Cai Chenxi %A Yan Zhang %A Min Zhang %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-cao26c %I PMLR %P 11120--11140 %U https://proceedings.mlr.press/v306/cao26c.html %V 306 %X The rapid evolution of generative models has unlocked new potentials in protein binder design, a pivotal task in structural biology, by facilitating end-to-end generation via joint sequence-structure modeling or hallucination. However, existing approaches are predominantly implemented under a single-target, single-state assumption, limiting their ability to model multi-target or multi-state interactions required for advanced function-oriented protein design. Here, we introduce Chamaileon, which unifies multi-target and multi-state binder design by formulating the problem as cross-context binding landscape modeling. The framework is underpinned by a training paradigm termed In-Context Complex Co-Design (I3CD) for context-aware sequence-structure co-modeling. During inference, we employ Mixture-of-Paths Sampling (MoPS), a scalable strategy that optimizes a single sequence across contexts while alleviating the scarcity of high-quality multi-conformational paired data. Extensive evaluation on our newly constructed benchmark, CROSS, demonstrates that Chamaileon effectively generates sequences adaptable to diverse conformational landscapes and multi-target requirements.
APA
Cao, H., Cheng, S., Liu, M., Huang, W., Lu, Y., Chenxi, C., Zhang, Y. & Zhang, M.. (2026). Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:11120-11140 Available from https://proceedings.mlr.press/v306/cao26c.html.

Related Material