Arrow Research search

Author name cluster

Yinan Yu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
2 author rows

Possible papers

2

AAMAS Conference 2026 Conference Paper

DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation

  • Shuai Wang
  • Dhasarathy Parthasarathy
  • Robert Feldt
  • Yinan Yu

Large language models (LLMs) perform well on general code generation but often struggle with domain-specific software tasks due to limitedspecializedknowledgeintheirtrainingdata. WeproposeDomAgent, an autonomous coding agent that enables domain-adapted code generation through structured reasoning and targeted retrieval. Its core module, DomRetriever, combines knowledge-graph reasoning with case-based reasoning to iteratively retrieve and synthesize relevant domain knowledge and examples. Experiments on the DS-1000 benchmark and real-world Volvo truck software development tasks show that DomAgent significantly improves domainspecific code generation, allowing small open-source models to approach the performance of large proprietary LLMs. The code is publicly available at: https: //github. com/Wangshuaiia/DomAgent.

PDF

ICRA Conference 2017 Conference Paper

Parse geometry from a line: Monocular depth estimation with partial laser observation

  • Yiyi Liao
  • Lichao Huang
  • Yue Wang 0020
  • Sarath Kodagoda
  • Yinan Yu
  • Yong Liu 0007

Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera. Although those platforms do not have sensors for 3D depth sensing capability, knowledge of depth is an essential part in many robotics activities. Therefore, recently, there is an increasing interest in depth estimation using monocular images. As this task is inherently ambiguous, the data-driven estimated depth might be unreliable in robotics applications. In this paper, we have attempted to improve the precision of monocular depth estimation by introducing 2D planar observation from the remaining laser range finder without extra cost. Specifically, we construct a dense reference map from the sparse laser range data, redefining the depth estimation task as estimating the distance between the real and the reference depth. To solve the problem, we construct a novel residual of residual neural network, and tightly combine the classification and regression losses for continuous depth estimation. Experimental results suggest that our method achieves considerable promotion compared to the state-of-the-art methods on both NYUD2 and KITTI, validating the effectiveness of our method on leveraging the additional sensory information. We further demonstrate the potential usage of our method in obstacle avoidance where our methodology provides comprehensive depth information compared to the solution using monocular camera or 2D laser range finder alone.

Details
v2026.09.13