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

Ryo Hachiuma

3 indexed papers

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

Publications per year

3
26

Top categories

Vision×2AI×2NLP×1

Frequent co-authors

Byung-Kwan Lee2×
Yu-Chiang Frank Wang2×
Rintaro Otsubo1×
Ryo Fujii1×
Reina Ishikawa1×
Taiki Kanaya1×

Research Timeline

2026
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

This paper introduces Zone of Proximal Policy Optimization (ZPPO) for knowledge distillation, which keeps the teacher inside the student's current zone of development and outperforms off/on-policy distillation and GRPO.

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

The paper introduces AnyGroundBench, a domain-adaptation benchmark for Spatio-Temporal Video Grounding, to evaluate the ability of Vision-Language Models to adapt to specialized domains.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIEmpiricalRecentJul 2, 2026

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

Rintaro Otsubo, Ryo Fujii, Reina Ishikawa, Taiki Kanaya +5 more

The paper introduces AnyGroundBench, a domain-adaptation benchmark for Spatio-Temporal Video Grounding, to evaluate the ability of Vision-Language Models to adapt to specialized domains.

View →
cs.CLEmpirical
Recent
Jun 16, 2026

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Byung-Kwan Lee, Ximing Lu, Shizhe Diao, Minki Kang +7 more

This paper introduces Zone of Proximal Policy Optimization (ZPPO) for knowledge distillation, which keeps the teacher inside the student's current zone of development and outperforms off/on-policy dis…

View →
cs.CVcs.AIEmpiricalRecentJun 11, 2026

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su +7 more

This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.

View →