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

Ufuk Topcu

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

AI×4Robotics×1Vision×1HCI×1

Frequent co-authors

Adam J. Thorpe2×
Stepan Tretiakov2×
Cheng-Hsi Hsiao2×
Su Ann Low2×
Xingjian Li2×
Hassan Iqbal2×

Research Timeline

2026
Physically Viable World Models: A Case for Query-Conditioned Embodied AI

The paper argues that for embodied AI to be safe and effective, world models must be physically viable, requiring a structural shift from mere observation prediction to representing the underlying physical dynamics sufficient to answer intervention queries.

Physically Viable World Models: A Case for Query-Conditioned Embodied AI

The paper argues that for embodied AI to be safe and effective, world models must be physically viable, requiring a structural shift from mere observation prediction to representing the underlying physical dynamics sufficient to answer intervention queries.

VEGAS: Human-Aligned Video Caption Evaluation via Gaze

The paper proposes VEGAS, a metric for video captioning that uses test-time gaze to sample personalized captions aligning with human focus.

Computing on the Fly: Navigating a Vision for the Future of Drone Computing

This paper identifies and discusses twelve technical challenges that need to be addressed to safely and effectively scale drone technology for commercial use.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.AISurveyRecentJul 21, 2026

Computing on the Fly: Navigating a Vision for the Future of Drone Computing

Kevin Butler, Christopher Stewart, Nils Aschenbruck, Alina Gerall +3 more

This paper identifies and discusses twelve technical challenges that need to be addressed to safely and effectively scale drone technology for commercial use.

View →
cs.CVcs.AIcs.HCEmpirical
Recent
Jul 9, 2026

VEGAS: Human-Aligned Video Caption Evaluation via Gaze

Shenghui Chen, Po-han Li, Ximeng Sun, Shijia Yang +4 more

The paper proposes VEGAS, a metric for video captioning that uses test-time gaze to sample personalized captions aligning with human focus.

View →
cs.AIRecentMay 28, 2026

Physically Viable World Models: A Case for Query-Conditioned Embodied AI

Adam J. Thorpe, Stepan Tretiakov, Cheng-Hsi Hsiao, Su Ann Low +5 more

The paper argues that for embodied AI to be safe and effective, world models must be physically viable, requiring a structural shift from mere observation prediction to representing the underlying phy…

View →
cs.AIRecentMay 28, 2026

Physically Viable World Models: A Case for Query-Conditioned Embodied AI

Adam J. Thorpe, Stepan Tretiakov, Cheng-Hsi Hsiao, Su Ann Low +5 more

The paper argues that for embodied AI to be safe and effective, world models must be physically viable, requiring a structural shift from mere observation prediction to representing the underlying phy…

View →