profile picture

Undergraduate at Halıcıoğlu Data Science Institute - UC SanDiego

Email GitHub LinkedIn CV

Profile photo credit to Scott Yang at the Salk Institute, taken at SfN 2025.

Research MISC

About Me

Hi! My name is Kaiwen Bian and I am a 4th year undergraduate student at UC SanDiego double majoring in Data Science and Cognitive Behavoral Neuroscience. My research interests sit at the intersection of embodied AI, computational neuroscience, and foundation models. I am fortunate to be advised by Talmo D. Pereira at the Salk Institute, Scott W. Linderman at Stanford University, and Yusu Wang and Gal Mishne at the Halıcıoğlu Data Science Institute.

Outside of my academic life, I enjoy skateboarding 🛹, surfing 🏄, and immersing myself in the serenity of the natural world 🌲

News

Mar 2026 — Our VNL subgroup in Dr. Pereira's lab will be presenting MIMIC-MJX at COSYNE 2026 — see you in Lisbon!
Mar 2026 — I will be presenting Code to Action: Motor Programs from Discrete Syllables in Whole-Body Biomechanical Control at SimBodies 2026 — see you at Janelia!
Mar 2026 — I will be presenting Beyond Flat Walks: Compositional Abstraction for Autoregressive Molecular Generation at Halıcıoğlu Data Science Institute (HDSI)'s Senior Capstone Showcase at UCSD — see you in San Diego!
Dec 2025 — Our VNL subgroup in Dr. Pereira's lab will be presenting Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics at NeurIPS 2025 — see you in San Diego!
Oct 2025 — I will be presenting Shaped by What's Missing: Topological Discovery of Behavioral Transitions at the Annual Society for Neuroscience (SfN) 2025 Conference — see you in San Diego!
Aug 2025 — I will be presenting MimicDyn: Dynamic Model for Planning & Generating Biomechanically Realistic Behaviors with Deep State Space Methods at the Stanford Undergraduate Research Program Symposium (SURP) 2025 — see you at Stanford!
Mar 2025 — Joining Professor Linderman's lab at Stanford University over the summer as an undergraduate research scholar for developing biomechanically realistic behavior generative models via State-Space Models.
Mar 2025 — Our VNL subgroup in Dr. Pereira's lab will be presenting our latest work on MIMIC-MJX at COSYNE 2025 — see you in Montréal!
May 2024 — Excited to be researching the theoretical aspect of Reinforcement & Continual Learning with advising from Professor Gao.
May 2024 — I will be presenting Multimodal Model Embodied Simulation at the 2024 annual UCSD FMP Symposium — see you in San Diego!
Dec 2023 — Joining Dr. Pereira's lab at the Salk Institute for Biological Studies as a research intern working on computational models of the brain using GPU-accelerated deep reinforcement learning.
Oct 2023 — Joining the URH/FMP program with advising from Dr. Trott.

Research Experience

2023 — Present

Research Intern

Salk Institute for Biological Studies
Crick-Jacobs Center for Theoretical and Computational Biology

Developing computationally efficient deep RL imitation systems (Mimic-MJX) for bio-mechanically realistic agents, discovering topological structure in embodied behavior spaces (TopoMimic), and building code-to-action embodied agents (Code2Act).

Advisor: Talmo D Pereira
2025 — Present

Visiting Research Scholar

Stanford University
Statistics Department & Wu Tsai Neurosciences Institute

Creating latent dynamical models for planning and generating bio-mechanically realistic behaviors using deep state-space modeling methods (MimicDyn). Co-advised on the Code2Act embodied agent project from Salk.

Advisor: Scott W Linderman
2022 — 2026

B.S. Data Science · B.S. Cognitive Behavioral Neuroscience

University of California, San Diego
Halıcıoğlu Data Science Institute

Graph compositional abstraction for molecular generation (MOSAIC) and topological analysis of embodied agent behaviors. Co-advised on the TopoMimic project from Salk.

Advisor: Yusu Wang, Gal Mishne