Kangqi (Kevin) Ni
I am an undergraduate student at Rice University majoring in Computer Science and Mathematics. My research focuses on designing high-performing, responsible AI solutions for social applications within language and vision domains. Specifically, I have worked in the following areas:
- Improving LLMs’ conversational and reasoning abilities in socially grounded contexts.
- Analyzing vision models’ biases in feature representations to promote responsible use.
During my undergraduate studies at Rice University, I am advised by Dr. Richard Baraniuk and Dr. Guha Balakrishnan.
In the past, I worked with Dr. Reid Simmons at Carnegie Mellon University on human-robot interaction and Dr. Joseph Young at Rice University on person re-identification and localization.
news
| Sep 20, 2024 | Our long paper Pedagogical Alignment of Large Language Models has been accepted to Findings of the Association for Computational Linguistics: EMNLP 2024. |
|---|---|
| Apr 13, 2024 | Our long paper Automated Long Answer Grading with RiceChem Dataset has been accepted to International Conference on Artificial Intelligence in Education (AIED) 2024. |
| Dec 13, 2023 | I have started my internship with the Machine Learning team at EdLight, PBC. |
| Jun 01, 2023 | I have joined the Robotics Institute Summer Scholars (RISS) 2023 program at Carnegie Mellon University. |
| Apr 28, 2023 | Our short paper Visualizing Chest X-ray Dataset Biases Using GANs has been accepted to Medical Imaging with Deep Learning (MIDL) 2023. |
publications
-
In Findings of the Association for Computational Linguistics: EMNLP, 2024 -
In International Conference on Artificial Intelligence in Education (AIED), 2024 -
In Medical Imaging with Deep Learning (MIDL), 2023 -
Estimating Causal Effects of Semantic Image Distortions on Deep Feature DistancesUnder Review, 2024
