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

Zhaoxiang Zhang

3 indexed papers

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

Publications per year

3
26

Top categories

NLP×2Robotics×1

Frequent co-authors

Xinkai Ma2×
Zhiqi Bai2×
Dingling Zhang2×
Pei Liu2×
Yishuo Yuan2×
He Zhu2×

Research Timeline

2026
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

World Pilot: Steering Vision-Language-Action Models with World-Action Priors

The paper presents World Pilot, a Vision-Language-Action framework that augments VLA models with priors from a World-Action Model to improve performance on manipulation tasks.

Highlighted terms show continued research focus across papers

Papers

cs.ROEmpiricalRecentJun 10, 2026

World Pilot: Steering Vision-Language-Action Models with World-Action Priors

Zefu Lin, Rongxu Cui, Junjia Xu, Xiaojuan Jin +3 more

The paper presents World Pilot, a Vision-Language-Action framework that augments VLA models with priors from a World-Action Model to improve performance on manipulation tasks.

View →
cs.CLRecentJun 1, 2026

TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

Xinkai Ma, Zhiqi Bai, Dingling Zhang, Pei Liu +20 more

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

View →
cs.CLRecentJun 1, 2026

TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

Xinkai Ma, Zhiqi Bai, Dingling Zhang, Pei Liu +20 more

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

View →