Individualized Cognitive Simulation
Modeling the unique, deeper thought processes and decision behaviors of a specific human being.
Research
Personalized language intelligence
My research asks how language models can better understand, adapt to, and simulate individuals or particular people rather than treating all users, speakers, and contexts with the same generic assumptions.
Topics
Current directions
Dialogue
Building interactive systems that reason over user goals, conversational history, preferences, and social context.
Token Compression
Studying compact representations that preserve the information models need while reducing context and computation costs.
Selected Work
Projects and papers
Individualized Cognitive Simulation
This project studies whether language models can simulate the deeper thought processes and decision behaviors of specific individuals rather than only imitating surface-level style. It introduces complementary benchmarks for authorial continuation and interview-based question answering, evaluating how linguistic, conceptual, and profile-based representations support individualized cognition.
Visual and token-efficient representations for NLP tasks
This project studies Vision-Text Augmentation (VTA), a complementary direction to vision-text compression where text is rendered into image space and varied through factors such as font, spacing, layout, and highlighting. Across information retrieval and question answering, visual composition changes substantially improve VLM performance while paraphrasing does not reliably improve LLMs. The work introduces VTAOpt, a model-agnostic Bayesian optimization framework that discovers effective rendering configurations without model tuning.
GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents
GameplayQA evaluates multimodal models in fast-paced 3D virtual environments where agents must track self state, other agents, world events, and temporally synchronized perspectives. The benchmark is designed to expose failures in temporal grounding, role attribution, and cross-video reasoning. Project website.
DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents
DiPS studies adaptive policy selection for persuasion agents in high-stakes dialogue settings. The system selects a persuasion policy from recent conversation state, conditions generation on strategy descriptions and retrieved examples, and evaluates whether the interaction reaches a successful outcome.
For the latest publication list, see my Google Scholar profile.