7 papers
FeatLens: Feature-Guided Dependency Retrieval for Repository-Level Code Generation
Xutian Li, Bo Xiong, Yifeng Zhu +6
Retrieving task-relevant code dependencies is critical for repository-level code generation. Existing approaches obtain dependency context through similarity-based retrieval, repos…
FeatX: Editing Software by Editing Features for Repository-Level Code Evolution
Xutian Li, Yifeng Zhu, Xianlin Zhao +3
Large language models (LLMs) are increasingly used for software evolution, yet most interaction paradigms remain code-centric and require manual context management and prompt itera…
RepoSummary: Feature-Oriented Summarization and Documentation Generation for Code Repositories
Yifeng Zhu, Xianlin Zhao, Xutian Li +4
Repository summarization is a crucial research question in development and maintenance for software engineering. Existing repository summarization techniques primarily focus on sum…
RoboSSM: Scalable In-context Imitation Learning via State-Space Models
Youngju Yoo, Jiaheng Hu, Yifeng Zhu +4
In-context imitation learning (ICIL) enables robots to learn tasks from prompts consisting of just a handful of demonstrations. By eliminating the need for parameter updates at dep…
LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations
Weikang Wan, Jiawei Fu, Xiaodi Yuan +2
Developing robotic systems capable of robustly executing long-horizon manipulation tasks with human-level dexterity is challenging, as such tasks require both physical dexterity an…
Efficient Sensorimotor Learning for Open-world Robot Manipulation
Yifeng Zhu
This dissertation considers Open-world Robot Manipulation, a manipulation problem where a robot must generalize or quickly adapt to new objects, scenes, or tasks for which it has n…
InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning
Muzhi Han, Yifeng Zhu, Song-Chun Zhu +2
Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predic…