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

Alex Pentland

3 indexed papers

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

Publications per year

3
26

Top categories

NLP×3AI×2Vision×2

Frequent co-authors

Zexue He3×
Pengyuan Li3×
Minglai Yang2×
Xinyan Velocity Yu2×
Xinyu Guo2×
Zhenting Qi2×

Research Timeline

2026
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that current state-of-the-art models fail on complex, domain-specific structures.

Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that current state-of-the-art models fail on complex, domain-specific structures.

Learning User Simulators with Turing Rewards

A new method for training user simulators using a Turing-Test-based reinforcement learning approach.

Highlighted terms show continued research focus across papers

Papers

cs.CLEmpiricalRecentJun 17, 2026

Learning User Simulators with Turing Rewards

Yingshan Susan Wang, Cedegao E. Zhang, Linlu Qiu, Zexue He +4 more

A new method for training user simulators using a Turing-Test-based reinforcement learning approach.

View →
cs.CLcs.AIcs.CVRecentMay 31, 2026

Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing

Minglai Yang, Xinyan Velocity Yu, Pengyuan Li, Xinyu Guo +21 more

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…

View →
cs.CLcs.AIcs.CVRecentMay 31, 2026

Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing

Minglai Yang, Xinyan Velocity Yu, Pengyuan Li, Xinyu Guo +21 more

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…

View →