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

Junyi Zhang

3 indexed papers

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

Publications per year

3
26

Top categories

AI×1NLP×1Robotics×1

Frequent co-authors

Jiaxin Ge2×
Trevor Darrell2×
Haiwen Feng2×
Tianning Chai1×
Hanjun Yoo1×
Chenyang Wang1×

Research Timeline

2026
T-Rex: Tactile-Reactive Dexterous Manipulation

The paper proposes a novel approach to tactile-reactive manipulation in robotic manipulation, introducing a large-scale dataset and a variable-rate Mixture-of-Transformers architecture.

Train An Imaginative Agent

A new training framework called Agima trains an agent to imagine and reason about the consequences of its actions before executing them.

KEEP-Bench: Evaluating Evidence Preservation in Context Compression

The authors introduce KEEP-Bench, a diagnostic benchmark to assess compression faithfulness and evaluate the performance of context compression models.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentOct 19, 2026

Train An Imaginative Agent

Jiaxin Ge, Junyi Zhang, Tianning Chai, Hanjun Yoo +8 more

A new training framework called Agima trains an agent to imagine and reason about the consequences of its actions before executing them.

View →
cs.CLEmpiricalRecent
Oct 19, 2026

KEEP-Bench: Evaluating Evidence Preservation in Context Compression

Ziqing Man, Di Wu, Jia-Chen Gu, Junyi Zhang +2 more

The authors introduce KEEP-Bench, a diagnostic benchmark to assess compression faithfulness and evaluate the performance of context compression models.

View →
cs.ROEmpiricalRecentJun 15, 2026

T-Rex: Tactile-Reactive Dexterous Manipulation

Dantong Niu, Zhuoyang Liu, Zekai Wang, Boning Shao +31 more

The paper proposes a novel approach to tactile-reactive manipulation in robotic manipulation, introducing a large-scale dataset and a variable-rate Mixture-of-Transformers architecture.

View →