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

Xinyu Mao

3 indexed papers

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

Publications per year

3
26

Top categories

ML×2Complexity×2AI×1

Frequent co-authors

Qian Li2×
Shang-Hua Teng2×
Yuhui Zeng1×
Xiaokun Liu1×
Wenyu Qin1×
Meng Wang1×

Research Timeline

2026
Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete

The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides sufficient positional information.

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete

The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides sufficient positional information.

CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning

This paper introduces CineCap, a framework for cinematographic captioning using structured reasoning, spatio-temporal anchors, and reinforcement learning.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentJun 23, 2026

CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning

Xinyu Mao, Yuhui Zeng, Xiaokun Liu, Wenyu Qin +5 more

This paper introduces CineCap, a framework for cinematographic captioning using structured reasoning, spatio-temporal anchors, and reinforcement learning.

View →
cs.LGcs.CCRecentJun 1, 2026

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete

Qian Li, Xinyu Mao, Shang-Hua Teng

The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides su…

View →
cs.LGcs.CCRecentJun 1, 2026

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete

Qian Li, Xinyu Mao, Shang-Hua Teng

The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides su…

View →