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

Mengdi Wang

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

AI×3ML×2Architecture×1NLP×1

Frequent co-authors

Yingcheng Wu3×
Zhe Zhao2×
Haibin Wen2×
Jiaming Ma2×
Yifan Wen2×
Jinglin Jian2×

Research Timeline

2026
Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery

The paper introduces Science Earth, a planet-scale scientific runtime that enables diverse, siloed AI capabilities to connect and collaborate dynamically, demonstrating that scientific discovery can become a distributed, self-correcting process.

Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery

The paper introduces Science Earth, a planet-scale scientific runtime that enables diverse, siloed AI capabilities to connect and collaborate dynamically, demonstrating that scientific discovery can become a distributed, self-correcting process.

EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents

EEVEE is a multi-dataset test-time prompt learning framework for LLM agents.

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

This paper introduces Skill Entropy, a measure of difficulty for switching between skills in long-horizon reasoning tasks, and proposes Skill^2-Bench, a benchmark for evaluating cross-skill long-horizon tasks. The authors also present Skill-Entropy RL, a reinforce learning framework using skill entropy as a training signal.

Rethinking Unified Memory for NPU-PIM Systems: Dual-View Memory for Dynamic Inference of LLM

This paper proposes PFM, a dual-view memory system for NPU-PIM systems that decouples physical data layout from accessor-visible logical views, reducing bandwidth underutilization and performance loss.

Highlighted terms show continued research focus across papers

Papers

cs.AREmpiricalRecentAug 7, 2026

Rethinking Unified Memory for NPU-PIM Systems: Dual-View Memory for Dynamic Inference of LLM

Shixin Zhao, Lian Liu, Tianhua Han, Mengdi Wang +2 more

This paper proposes PFM, a dual-view memory system for NPU-PIM systems that decouples physical data layout from accessor-visible logical views, reducing bandwidth underutilization and performance loss…

View →
cs.CLcs.LGEmpirical
Recent
Aug 5, 2026

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Yinghui He, Ling Yang, Jiarui Liu, Yongjin Yang +5 more

This paper introduces Skill Entropy, a measure of difficulty for switching between skills in long-horizon reasoning tasks, and proposes Skill^2-Bench, a benchmark for evaluating cross-skill long-horiz…

View →
cs.LGcs.AIEmpiricalRecentJun 9, 2026

EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents

Weixian Xu, Shilong Liu, Mengdi Wang

EEVEE is a multi-dataset test-time prompt learning framework for LLM agents.

View →
cs.AIRecentMay 31, 2026

Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery

Zhe Zhao, Haibin Wen, Yingcheng Wu, Jiaming Ma +9 more

The paper introduces Science Earth, a planet-scale scientific runtime that enables diverse, siloed AI capabilities to connect and collaborate dynamically, demonstrating that scientific discovery can b…

View →
cs.AIRecentMay 31, 2026

Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery

Zhe Zhao, Haibin Wen, Yingcheng Wu, Jiaming Ma +9 more

The paper introduces Science Earth, a planet-scale scientific runtime that enables diverse, siloed AI capabilities to connect and collaborate dynamically, demonstrating that scientific discovery can b…

View →