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

Wenxuan Zhang

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Vision×1

Frequent co-authors

Xingyu Qu1×
Peng Hu1×
Chen He1×
Yuhao Wu1×
Lei Wang1×
Fumin Shen1×

Research Timeline

2026
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces

The paper identifies and demonstrates that post-conclusion continuation in answer-correct long-CoT traces is harmful during LLM fine-tuning, proposing a method to cut this continuation.

Collaborative Space Object Detection with Multi-Satellite Viewpoints in LEO Constellations

This paper demonstrates that fusing multi-viewpoint data from multiple satellites significantly enhances the accuracy of space object detection in congested LEO constellations, establishing multi-view fusion as an effective strategy.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIRecentJun 1, 2026

Collaborative Space Object Detection with Multi-Satellite Viewpoints in LEO Constellations

Xingyu Qu, Wenxuan Zhang, Peng Hu

This paper demonstrates that fusing multi-viewpoint data from multiple satellites significantly enhances the accuracy of space object detection in congested LEO constellations, establishing multi-view…

View →
cs.AIRecentMay 28, 2026

Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces

Chen He, Yuhao Wu, Lei Wang, Wenxuan Zhang +1 more

The paper identifies and demonstrates that post-conclusion continuation in answer-correct long-CoT traces is harmful during LLM fine-tuning, proposing a method to cut this continuation.

View →