• Homepage
  • Home
  • Notebook
  • Projects
  • Fun Facts
    Ruoxi Ning

    Ruoxi Ning

    MMath, University of Waterloo

    • Waterloo, ON, Canada
    • Email
    • Twitter
    • Github
    • Google Scholar
    • rxning0530

    Projects

    NovelQA cover ICLR 2025

    NovelQA

    A long-context benchmark with 2,305 questions over novels averaging 200K+ tokens, covering question answering, retrieval, and reasoning.

    Abstract placeholder image for VLM-Lens

    VLM-Lens

    Probes and test cases for Qwen-VL and InternLM, with a focus on color naming, language gaps, and modality gaps in vision-language models.

    Abstract placeholder image for GLoRE

    GLoRE

    A unified logical reasoning benchmark and evaluation pipeline across datasets such as LogiQA, ReClor, FOLIO, AR-LSAT, ProofWriter, and RuleTaker.

    Abstract placeholder image for Latinate-Germanic Ratio

    Latinate-Germanic Ratio

    A linguistically grounded metric for genre formality using 40K etymology entries and Brown-family corpora, reaching strong correlation with existing formality scores.