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

Marco Pavone

3 indexed papers

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

Publications per year

3
26

Top categories

Robotics×3AI×2Vision×2ML×1

Frequent co-authors

Apoorva Sharma2×
Edward Schmerling2×
Sushant Veer2×
Jadelynn Dao1×
Milan Ganai1×
Yasmina Abukhadra1×

Research Timeline

2026
StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement

StressDream proposes a novel method to steer video world model imaginations toward high-impact, yet plausible outcomes, enabling robust policy evaluation and improvement by identifying undesirable future scenarios.

X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation

This paper introduces X4Val, a framework for variance-reduced real-world metric estimation using non-paired, multi-domain data.

DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?

This paper introduces DIRECT, a routing framework that allocates test-time compute per prompt to improve the success--cost Pareto frontier for embodied agents.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.AIcs.CVEmpiricalRecentJun 10, 2026

DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?

Jadelynn Dao, Milan Ganai, Yasmina Abukhadra, Ajay Sridhar +6 more

This paper introduces DIRECT, a routing framework that allocates test-time compute per prompt to improve the success--cost Pareto frontier for embodied agents.

View →
cs.RORecentJun 3, 2026

X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation

Rachel Luo, Michael Watson, Apoorva Sharma, Heng Yang +5 more

This paper introduces X4Val, a framework for variance-reduced real-world metric estimation using non-paired, multi-domain data.

View →
cs.CVcs.AIcs.LGRecentMay 29, 2026

StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement

Junwon Seo, Sushant Veer, Ran Tian, Wenhao Ding +5 more

StressDream proposes a novel method to steer video world model imaginations toward high-impact, yet plausible outcomes, enabling robust policy evaluation and improvement by identifying undesirable fut…

View →