Jingru Yang — accepted AI-conference papers

2026

Modeling the Visual Ambiguity of Human Sketches

Yang Zhou, Ping Ni, Jin Wang, Senyun Jia, Jingdan Yan, Kaixiang Huang +3

CVPR 2026

Human sketches provide a compact and expressive form of visual communication, but their sparse structural cues, while capturing essential object structures, introduce ambiguity because a single sketch can correspond to multiple plausible images, making cross-domain alignment uncertain and unstable.

Cited by 0 Source ↗Scholar ↗

2025

Jury-and-Judge Chain-of-Thought for Uncovering Toxic Data in 3D Visual Grounding

Kaixiang Huang, Qifeng Zhang, Jin Wang, Jingru Yang, Yang Zhou, Huan Yu +2

NeurIPS 2025poster

3D Visual Grounding (3DVG) faces persistent challenges due to coarse scene-level observations and logically inconsistent annotations, which introduce ambiguities that compromise data quality and hinder effective model supervision. To address these challenges, we introduce Refer-Judge, a novel framew…

Cited by 0 Source ↗code ↗Scholar ↗