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

Zheqi Lv

3 indexed papers

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

Publications per year

3
26

Top categories

Vision×3AI×3NLP×1Multimedia×1

Frequent co-authors

Mingjian Gao2×
Wenqiao Zhang2×
Yuqian Yuan2×
Yang Dai2×
Binhe Yu2×
Haoyu Zheng2×

Research Timeline

2026
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vision-Language-Action policies.

VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vision-Language-Action policies.

Training-Free Semantic Correction for Autoregressive Visual Models

The paper proposes Gazer, a framework that integrates multimodal large language model feedback into the AVM sampling loop for in-generation semantic correction.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.CLEmpiricalRecentJun 21, 2026

Training-Free Semantic Correction for Autoregressive Visual Models

Junhao Chen, Chanyu Zhu, Zheqi Lv, Keting Yin +1 more

The paper proposes Gazer, a framework that integrates multimodal large language model feedback into the AVM sampling loop for in-generation semantic correction.

View →
cs.CVcs.AIRecent
May 28, 2026

VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

Mingjian Gao, Wenqiao Zhang, Yuqian Yuan, Yang Dai +8 more

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vi…

View →
cs.CVcs.AIRecentMay 28, 2026

VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

Mingjian Gao, Wenqiao Zhang, Yuqian Yuan, Yang Dai +8 more

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vi…

View →