hey, i'm nishkal
cs + math @ UMD, trying to actually understand how ai works under the hood.
right now, i'm digging into mixture of experts (MoEs), interpreting the inner workings of these models and aiming for extreme domain specialization. recently, i submitted a paper with preliminary work on this topic to ICLR 2025 (SLLM workshop). you can check out the paper here. i’m also starting to explore unfaithfulness in reasoning models in an attempt to develop techniques to detect motivated reasoning.
i'm currently interning at mindgrasp, where i'm building ai-powered study tools to help students learn more efficiently (and maybe procrastinate a little less). i also lead the ai/ml club at UMD, where we run workshops, speaker events, and semester-long projects to help students get hands-on with machine learning research and applications.
previous quests
previously, i worked with the RISE Lab on tropical cyclone modeling and storm data imputation we even published a paper from that project!
i also worked with the Center for Disaster Resilience at UMD on writing and optimizing simulation logic for flood insurance programs.
and i built DenseTeX, a model that converts images of math into LaTeX (mostly works). i also served as a teaching assistant for discrete mathematics.
i'm always down to chat about sparse models, interpretability, llms, weird math problems, or why Jet Lag: The Game is absolute peak content.