2 citations · 4 across the 5 of their papers we have counts for
7 papers
Requested, Executed and Recoverable Credit: Shared Action Ordering among LLM Borrowers in a Simulated Lending Market
Victoria Ruojie Li
We test whether shared action ordering changes executed credit in a simulated collateralized lending market. Three small open-weight language models face a borrowing cap that value…
Shared Models, Selective Trading, and Order Flow
Victoria Ruojie Li, Arka Prava Bandyopadhyay
We study whether model diversity survives selection into trading. In synthetic markets with a fixed mixture of three language-model families, news presentation changes their repres…
The Potential and Limitations of Vision-Language Models for Human Motion Understanding: A Case Study in Data-Driven Stroke Rehabilitation
Victor Li, Naveenraj Kamalakannan, Avinash Parnandi +2
Vision-language models (VLMs) have demonstrated remarkable performance across a wide range of computer-vision tasks, sparking interest in their potential for digital health applica…
Does visualization help AI understand data?
Victoria R. Li, Johnathan Sun, Martin Wattenberg
Charts and graphs help people analyze data, but can they also be useful to AI systems? To investigate this question, we perform a series of experiments with two commercial vision-l…
Can Interpretation Predict Behavior on Unseen Data?
Victoria R. Li, Jenny Kaufmann, Tian Qin +3
Interpretability research often predicts model responses to targeted mechanistic interventions. But can we predict responses to unseen input data? We propose and demonstrate this a…
REVEAL: Robust Evolution of Vision-Language Models for Explainable AI-Video Detection
Qingyuan Liu, Yun-Yun Tsai, Ruijian Zha +4
The rapid advancement of AI-generated video poses challenges to digital authenticity and security. Current detection methods, often trained on specific datasets, struggle with the…
ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context
Victoria R. Li, Yida Chen, Naomi Saphra
While the biases of language models in production are extensively documented, the biases of their guardrails have been neglected. This paper studies how contextual information abou…