Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Haoyuan Shi

Haoyuan Shi

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2Vision×1

Frequent co-authors

Jinpeng Lu3×
Yinda Chen3×
Yi Zhang3×
Yong Dai3×
Xiaozhu Ju3×
Xiancong Ren2×

Research Timeline

2026
VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at visual grounding, they struggle with fine-grained semantic following.

VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at visual grounding, they struggle with fine-grained semantic following.

Current World Models Lack a Persistent State Core

WRBench introduces a new benchmark for evaluating world models

Highlighted terms show continued research focus across papers

Papers

cs.CVEmpiricalRecentJun 18, 2026

Current World Models Lack a Persistent State Core

Jinpeng Lu, Dexu Zhu, Haoyuan Shi, Linghan Cai +7 more

WRBench introduces a new benchmark for evaluating world models

View →
cs.AIRecentMay 28, 2026

VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing

Haoyuan Shi, Xiancong Ren, Yingji Zhang, Qinfan Zhang +8 more

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at vi…

View →
cs.AIRecentMay 28, 2026

VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing

Haoyuan Shi, Xiancong Ren, Yingji Zhang, Qinfan Zhang +8 more

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at vi…

View →