10 citations · 10 across the 7 of their papers we have counts for
7 papers · 1 filter
ChartRevise: A Dataset and Evaluation Protocol for Exact Chart Editing via Code
Jiaxiang Tang, Yi Zhou, Chad DeLuca +5
Chart editing requires cross-modal edit grounding, realizing a requested visual change in the code that draws it, with necessary related updates and without altering unrelated cont…
StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies
Wenzhuo Li, Qiongfeng Shi, Yi Zhou
Memory-dependent robotic manipulation often requires later actions to use information from earlier interactions. Existing vision-language-action (VLA) policies primarily rely on cu…
OrthoSkillVLA: Continual Skill Learning via Gradient-Informed Skill Subspace Adaptation
Jiaqi Wang, Zhou Fang, Qiongfeng Shi +1
Pretrained Vision-Language-Action models provide a strong foundation for robot learning, but sequentially adapting them to diverse skills can perturb the representations and veloci…
An Exploratory Study on LLM-Generated Code and Comments in Code Repositories
Yongyi Ji, Jiaji Wang, Yi Zhou +2
The use of LLMs in software development has become increasingly widespread on tasks such as code generation and summarization. Reports from large technology companies showed that a…
A Systematic Approach for Large Language Models Debugging
Basel Shbita, Anna Lisa Gentile, Bing Zhang +10
Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging…
ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models
Zhou Fang, Jiaqi Wang, Yi Zhou +2
Vision-Language-Action (VLA) policies increasingly use Flow Matching (FM) action heads to generate action chunks as continuous trajectories. At inference, an FM head solves an ordi…
Evaluating Ill-Defined Tasks in Large Language Models
Yi Zhou, Basel Shbita
Many evaluations of Large Language Models (LLMs) target tasks that are inherently ill-defined, with unclear input and output spaces and ambiguous success criteria. We analyze why e…