Projects

Node Perturbation for Gradient-Free Fine-Tuning of Large Language Models I'm currently working as an AI researcher at the Brain and Cognitive Sciences Department at MIT, where I'm finetuning LLMs with mechanisms inspired by the brain! Typical fine-tuning techniques include supervised learning and reinforcement learning with human feedback (RLHF). These methods are effective but time intensive, especially with their reliance on back propagation. RL also often correlates with reward-hacking and can be unstable. Not to mention that the reliance on back propagation and partial derivates translates poorly to the processes that occur in the brain! My research explores how we can emulate the brain's own learning mechanisms to fine-tune LLMs. In particular, we are utilizing evolutionary algorithms (evolution strategies) to fine-tune LLMs. The results are promising, as we demonstrate that evolution strategies can scale efficiently and result in similar performance to RL policies like GRPO, but using mechanisms such as node and weight perturbation.

Computationally Emulating the Evolution of Eyesight using Reinforcement Learning I worked as an AI/ML undergraduate researcher at the Media Lab (Camera Culture group). I expanded an existing reinforcement learning (RL) framework in Python, PyTorch, and MuJoCo by training agents across diverse environments (multi-eye perception, adversarial setups) to test robustness and adaptability in navigation tasks. I also discovered an emergent dragonfly prediction strategy, where agents anticipated goal locations before arrival, demonstrating RL's ability to uncover novel optimization behaviors. I engineered a hybrid approach combining supervised models (CNNs, MLPs) with RL by passing distance-to-goal predictions as inputs, improving learning efficiency and enabling multisensory input modeling. I finally validated the approach through trajectory mapping and performance benchmarking, achieving competitive results with baseline RL while reducing training complexity