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

Fan Zhang

8 indexed papers

Recent (6 mo)
7
With code
0
Influential cites
0
Benchmarked
0

Publications per year

8
26

Top categories

Vision×4AI×4NLP×3Multimedia×2Crypto×2HCI×1ML×1Robotics×1

Frequent co-authors

Yi-Fan Zhang3×
Xingyu Lu2×
Jinpeng Wang2×
Yankai Yang2×
Yancheng Long2×
Yiyang Fan2×

Research Timeline

2026
Perils of Parallelism: Transaction Fee Mechanisms under Execution Uncertainty

The paper analyzes transaction fee mechanisms in modern blockchains that use parallel execution and contingency, proving an inherent trade-off between minimizing risks for users and maximizing revenue for schedulers.

Privacy-Preserving Screening for Record Linkage

The paper introduces Appraisal, a novel Screening-then-Linkage framework (PPRS) that significantly improves the scalability and efficiency of Privacy-Preserving Record Linkage by incorporating a lightweight screening phase.

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains

The paper proposes a new pipeline for audio-visual Question Answering that addresses issues with current methods by transforming videos into structured scripts and using clues to generate QA pairs.

Can Agentic Trading Systems Pay for Their Own Intelligence?

The paper introduces TradeLens, a toolkit for evaluating the agentic viability of large language model agents in trading systems by reconstructing trading trajectories and diagnosing intelligence-to-profit conversion.

TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations

This paper introduces TrackEverything, a 3D point tracker that breaks the trade-off between tracking sparse points over long horizons and tracking all points across short clips.

A prospective randomized study of patient-centered AI for clinical visit preparation

A large language model-based chatbot improved patient visit preparation and satisfaction.

Highlighted terms show continued research focus across papers

Papers

cs.HCcs.CLcs.LGEmpiricalRecentOct 30, 2026

A prospective randomized study of patient-centered AI for clinical visit preparation

Xincheng Tan, Matthew Thompson, Xiang Ji, Angelica Willis +32 more

A large language model-based chatbot improved patient visit preparation and satisfaction.

View →
cs.CVcs.AIcs.ROEmpirical
Recent
Sep 24, 2026

TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations

Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta, Fan Zhang +4 more

This paper introduces TrackEverything, a 3D point tracker that breaks the trade-off between tracking sparse points over long horizons and tracking all points across short clips.

View →
cs.AIcs.MAEmpiricalRecentJul 11, 2026

Can Agentic Trading Systems Pay for Their Own Intelligence?

Qiqi Duan, Changlun Li, Chen Wang, Fan Zhang +9 more

The paper introduces TradeLens, a toolkit for evaluating the agentic viability of large language model agents in trading systems by reconstructing trading trajectories and diagnosing intelligence-to-p…

View →
cs.CVEmpiricalRecentJun 12, 2026

OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains

Xinyue Cai, Chaoyou Fu, Yi-Fan Zhang, Ran He +1 more

The paper proposes a new pipeline for audio-visual Question Answering that addresses issues with current methods by transforming videos into structured scripts and using clues to generate QA pairs.

View →
cs.CVcs.AIcs.CLRecentMay 27, 2026

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

Xingyu Lu, Jinpeng Wang, Yi-Fan Zhang, Yankai Yang +12 more

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multim…

View →
cs.CVcs.AIcs.CLRecentMay 27, 2026

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

Xingyu Lu, Jinpeng Wang, Yi-Fan Zhang, Yankai Yang +12 more

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multim…

View →
cs.CRRecentMay 26, 2026

Privacy-Preserving Screening for Record Linkage

Chenyu Huang, Fan Zhang, Huangxun Chen, Yongjun Zhao +3 more

The paper introduces Appraisal, a novel Screening-then-Linkage framework (PPRS) that significantly improves the scalability and efficiency of Privacy-Preserving Record Linkage by incorporating a light…

View →
cs.CRcs.GTApr 5, 2026

Perils of Parallelism: Transaction Fee Mechanisms under Execution Uncertainty

Sarisht Wadhwa, Aviv Yaish, Fan Zhang, Kartik Nayak

The paper analyzes transaction fee mechanisms in modern blockchains that use parallel execution and contingency, proving an inherent trade-off between minimizing risks for users and maximizing revenue…

View →