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

Zhihan Zhang

4 indexed papers

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

Publications per year

4
26

Top categories

AI×4NLP×2Architecture×1

Frequent co-authors

Rongzhi Zhang2×
Rui Feng2×
Jingfeng Yang2×
Qingyu Yin2×
Xin Liu2×
Zixuan Zhang2×

Research Timeline

2026
QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in RL performance.

QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in RL performance.

Embedded Arena: Iterative Optimization via Hardware Feedback

This paper introduces a hardware-in-the-loop agent that optimizes AI models for heterogeneous microcontrollers.

Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation

This paper proposes a new method, TPAE, to improve multimodal reasoning in large language models by providing fine-grained supervision signals.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentSep 30, 2026

Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation

Zhihan Zhang, Lizi Liao

This paper proposes a new method, TPAE, to improve multimodal reasoning in large language models by providing fine-grained supervision signals.

View →
cs.ARcs.AIEmpiricalRecent
Jun 15, 2026

Embedded Arena: Iterative Optimization via Hardware Feedback

Zhihan Zhang, Alexander Le Metzger, Jiuyang Lyu, Chun-Cheng Chang +9 more

This paper introduces a hardware-in-the-loop agent that optimizes AI models for heterogeneous microcontrollers.

View →
cs.CLcs.AIRecentJun 2, 2026

QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards

Rongzhi Zhang, Rui Feng, Zhihan Zhang, Jingfeng Yang +7 more

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in…

View →
cs.CLcs.AIRecentJun 2, 2026

QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards

Rongzhi Zhang, Rui Feng, Zhihan Zhang, Jingfeng Yang +7 more

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in…

View →