edit RL project link in about

Author: codez266

_pages/about.md

@@ -32,7 +32,7 @@ latest_posts:
 
 Thank you dear visitor for stopping by! I am a final year PhD candidate at University of Michigan, Ann Arbor. My research focus and interests are at the intersection of Machine Learning and Human-Computer Interaction (HCI).
 
-I develop adaptive AI systems that <span style="color:deeppink;">enable people to reason under risk and uncertainty in complex decision-making scenarios</span> by modeling their underlying thought processes and not just their observable behaviors. For example, in education, inferring students' conceptual gaps requires reconstructing their mental models from their learning trajectories, not just identifying surface-level mistakes. I borrow from <span style="color: deeppink">cognitive science and probabilistic machine learning</span> to design AI with experts' mental model to improve Human-AI interaction. By modeling people's latent cognitive states, my methods <span style="color: deeppink">improve reasoning of AI systems beyond observed behaviors</span>, improving overall learning efficiency and accuracy. I bring in strong computational and model building skills from my prior industry experience to build systems for Human-AI interaction and my training in HCI allows me to conduct large scale evaluations in people's work context for improving Human-AI interaction. For example, I recently built a bayesian network from a massive dataset of 3M records to model personal information and using it to study personalization - privacy trade-off. I have also applied my strong Reinforcement Learning (RL) foundations to modeling human behavior, which positions me well to explore RL-based fine-tuning of LLMs. For instance, I developed a [deep RL system](behavior_modeling/) from scratch to simulate indoor human behavior and COVID-19 transmission dynamics (code available on request), demonstrating how RL can capture and reason about complex behavioral patterns. The following three broad directions describe my research focus and future vision.
+I develop adaptive AI systems that <span style="color:deeppink;">enable people to reason under risk and uncertainty in complex decision-making scenarios</span> by modeling their underlying thought processes and not just their observable behaviors. For example, in education, inferring students' conceptual gaps requires reconstructing their mental models from their learning trajectories, not just identifying surface-level mistakes. I borrow from <span style="color: deeppink">cognitive science and probabilistic machine learning</span> to design AI with experts' mental model to improve Human-AI interaction. By modeling people's latent cognitive states, my methods <span style="color: deeppink">improve reasoning of AI systems beyond observed behaviors</span>, improving overall learning efficiency and accuracy. I bring in strong computational and model building skills from my prior industry experience to build systems for Human-AI interaction and my training in HCI allows me to conduct large scale evaluations in people's work context for improving Human-AI interaction. For example, I recently built a bayesian network from a massive dataset of 3M records to model personal information and using it to study personalization - privacy trade-off. I have also applied my strong Reinforcement Learning (RL) foundations to modeling human behavior, which positions me well to explore RL-based fine-tuning of LLMs. For instance, I developed a <a href="{{ site.baseurl }}/behavior_modeling" target="_blank">deep RL system</a> from scratch to simulate indoor human behavior and COVID-19 transmission dynamics (code available on request), demonstrating how RL can capture and reason about complex behavioral patterns. The following three broad directions describe my research focus and future vision.
 
 1. <b>Desiging computational models that can understand and improve expert decision-making</b> <span style="color:deeppink;">(AI to critique not obey)</span>: Furthering the design of computational models that can <span style="color:deeppink;">understand and reason about experts' decision processes, and how they reason about and balance principles in their decisions</span>. For example, understanding how instructors balance providing the answer versus guiding students in tutoring scenarios.