Research

You can find more of my work and thinking in my blog.

• 
  The Emergence of Complex Behavior in Large-Scale Ecological Environments[arxiv][code][news]2025

  Joseph Bejjani, Chase Van Amburg, Chengrui Wang, Chloe Huangyuan Su, Sarah M. Pratt, Yasin Mazloumi, Naeem Khoshnevis, Sham M. Kakade, Kianté Brantley, Aaron Walsman

• 
  DIRT: The Distributed Intelligent Replicator Toolkit[code]2025

  Poster, International Conference on Artificial Life

  Chengrui Wang, Chase Van Amburg, Chloe Huangyuan Su, Joseph Bejjani, Sarah M. Pratt, Yasin Mazloumi, Naeem Khoshnevis, Sham M. Kakade, Kianté Brantley, Aaron Walsman

• 
  When Agents Prefer Hacking To Failure: Evaluating Misalignment Under Pressure[lesswrong][talk]2025

  Joseph Bejjani, Itamar Rocha Filho, Haichuan Wang, Zidi Xiong

• Programmatic Interpretability for Reward Model Debugging[pdf][code]2025

  Joseph Bejjani, Max Peng, Kayden Kehe

• Evolutionary Alignment[pdf][code]2025

  Joseph Bejjani*, Itamar Rocha Filho*, Core Francisco Park

• Explain This, Pruner! The Effect of Zero-Order Pruning on LLM Explainability and Curvature[paper][code]2025

  The Harvard Undergraduate Research Journal, Vol. 15, No. 2

  Joseph Bejjani, Camilo Brown-Pinilla, David Ettel

• 
  Large Motion Diffusion Models[code][talk]2025

  Camilo Brown-Pinilla, Joseph Bejjani

• Prune As You Tune: LoRA-Enabled Model Compression[code]2024

  Joseph Bejjani, Amulya Garimella, Swati Goel, Mohammed Sakib

* equal contribution