GenMech Lab logo
GenMech Lab Generative Mechanics

Generative Mechanics

Generative Mechanics: designing Matter, guiding Making, and inspiring Mind.

GenMech large logo

A personal research lab and vision that unites generative AI (diffusion • LLMs • agents) with physics‑based modeling to understand complex materials, design proteins and alloys, and optimize additive manufacturing with agentic reinforcement learning (RL).

About

Headshot
140×140
PNG/JPG

Bo Ni, Ph.D. — Founder of the GenMech Lab (personal research initiative). This site reflects my independent research vision that extends beyond roles at current and prior institutions (e.g., CMU, MIT & Brown). I explore Generative Mechanics, a rigorous partnership between learning and physical law to understand, design, and make complex materials.

Focus
Proteins • Alloys (AM) • 2D materials
Methods
Diffusion • LLMs • RL • Agents • DFT/MD/FEM/PF/CALPHAD
Goal
Predictive & creative mechanics
CV Google Scholar GitHub

Vision

I aim to rebuild mechanics by coupling generative AI with physics‑based modeling. Complex materials blend deterministic laws with statistical behavior. Generative models map vast design spaces; multiscale mechanics reveals governing physics. This synthesis—Generative Mechanics—seeks a science that is both predictive and creative.

Proteins Alloys (AM) 2D Materials Diffusion Models LLMs Reinforcement Learning Constitutive Laws Invariants Multiscale
Generative Science
Constitutive discovery, invariants, symmetry across scales.
Intelligent Design
Physics‑in‑the‑loop inverse design for proteins, alloys, 2D materials.
Reliable Making
Agentic RL + digital twins for robust AM optimization.

Research Highlights

AlloyGPT visual
Physics‑in‑the‑loop alloy design.

AlloyGPT for AM

End‑to‑end alloy design with LM‑driven learning + generation. npj Computational Materials (2025)

ForceGen visual
Mechanics‑aware protein language diffusion.

Protein generation from mechanics

End‑to‑end de novo protein generation grounded in nonlinear unfolding responses. Science Advances (2024)

MechAgents visual
LLM multi‑agent tool use + simulation.

LLM multi‑agent mechanics

Teams of language agents plan, simulate, and integrate knowledge to solve mechanics problems and generate data. Extreme Mechanics Letters (2024)

Protein diffusion design
Generative constraints for structure.

Protein diffusion design

Attention‑based diffusion under secondary‑structure constraints. Chem (2023)

Publications

    Reviews and previews

  1. Ni, B. and Buehler, M.J., 2025. Agentic End-to-End De Novo Protein Design for Tailored Dynamics Using a Language Diffusion Model. arXiv preprint arXiv:2502.10173, under review. [code]
  2. Ni, B., and Taheri-Mousavi, S. M., 2025. Accelerate materials discovery and design via generative artificial intelligence, under review.

    3. Research articles

  3. Ni, B., Glaser, B., Taheri-Mousavi, S. M., 2025. End-to-end prediction and design of additively manufacturable alloys using a generative AlloyGPT model. npj Computational Materials, 11(1), 294. [code] (Highlighted by CMU News)
  4. 4.Shin, B.*, Ni, B.*, Toh C.*, Steinbach, D., Yang, Z., Sassi, L., Ai, Q., Niu, K., Lin, J., Suenaga, K., Han, Y., Buehler, M.J., Özyilmaz, B. and Lou, J., 2025. Intrinsic toughening in monolayer amorphous carbon nanocomposites. Matter. (*Co-first authors) (Highlighted by Rice News)
  5. Ni, B. and Buehler, M.J., 2024. MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge. Extreme Mechanics Letters, 67, p.102131. [code]
  6. Ni, B., Kaplan, D.L. and Buehler, M.J., 2024. ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion model. Science Advances 10(6): eadl4000. [code]
  7. Ni, B., Kaplan, D.L. and Buehler, M.J., 2023. Generative design of de novo proteins based on secondary-structure constraints using an attention-based diffusion model. Chem, 9(7), pp.1828–1849. (Selected as the issue cover) (Highlighted by MIT news) [code]
  8. Liu, F.Y., Ni, B. and Buehler, M.J., 2022. PRESTO: Rapid protein mechanical strength prediction with an end-to-end deep learning model. Extreme Mechanics Letters, 55, p.101803.
  9. Yang, Y., Song, Z., Lu, G., Zhang, Q., Zhang, B., Ni, B., Wang, C., Li, X., Gu, L., Xie, X. and Gao, H., 2021. Intrinsic toughening and stable crack propagation in hexagonal boron nitride. Nature, 594(7861), pp.57-61.
  10. Ni, B. and Gao, H., 2020. Engineer energy dissipation in 3D graphene nanolattice via reversible snap-through instability. Journal of Applied Mechanics, 87(3), p.031012.
  11. Guo, K.*, Ni, B.* and Gao, H., 2020. Tuning crack-inclusion interaction with an applied T-stress. International Journal of Fracture, 222(1-2), pp.13-23. (*Co-first authors)
  12. Ni, B. and Gao, H., 2021. A deep learning approach to the inverse problem of modulus identification in elasticity. MRS Bulletin, 46, pp.19-25.
  13. Li, J., Ni, B., Zhang, T. and Gao, H., 2018. Phase field crystal modeling of grain boundary structures and growth in polycrystalline graphene. Journal of the Mechanics and Physics of Solids, 120, pp.36-48.
  14. Hacopian, E.F.*, Yang, Y.*, Ni, B.*, Li, Y., Li, X., Chen, Q., Guo, H., Tour, J.M., Gao, H. and Lou, J., 2018. Toughening graphene by integrating carbon nanotubes. ACS Nano, 12(8), pp.7901-7910. (*Co-first authors) (Highlighted by Rice News)

    15. Reviews and previews

  15. Luu, R. K., Arevalo, S., Lu, W., Ni, B., Yang, Z., Shen, S. C., Berkovich, J., Hsu, Y.-C., Zan, S., & Buehler, M. J. (2024). Learning from Nature to Achieve Material Sustainability: Generative AI for Rigorous Bio-inspired Materials Design. An MIT Exploration of Generative AI, March.
  16. Ni, B.*, Steinbach, D.*, Yang, Z., Lew, A., Zhang, B., Fang, Q., Buehler, M.J. and Lou, J., 2022. Fracture at the two-dimensional limit. MRS Bulletin, 47(8), pp.848-862. (*Co-first authors)
  17. Ni, B. and Gao, H., 2021. Breaking two-dimensional polymeric crystals. Matter, 4(3), pp.763-765.
  18. Ni, B. and Gao, H., 2020. Harness the power of fracture: controlled fragmentation of graphene via substrate necking. Matter, 2(3), pp.521-524.

    19. Book chapter

  19. Ni, B.*, Zhang, T.*, Li, J., Li, X., and Gao, H., 2019. Topological design of graphene. Handbook of Graphene, Volume 2: Physics, Chemistry, and Biology, Wiley, DOI: 10.1002/9781119468455.ch19. (*Co-first authors)

Contact

Email:

General inquiries, media, and academic/industry discussions welcome.

Links

Google Scholar · GitHub · Portfolio