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

Dong Zhang

10 indexed papers

Recent (6 mo)
10
With code
0
Influential cites
0
Benchmarked
0

Publications per year

10
26

Top categories

AI×5Vision×3Crypto×2Robotics×1ML×1NLP×1Social Networks×1

Frequent co-authors

Xudong Zhang4×
Yifan Ye1×
Yankai Fu1×
Yaoxu Lv1×
Bohan Hou1×
Jun Cen1×

Research Timeline

2026
Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection

This paper measures the prevalence of recurring vulnerability patterns (variants) across multiple AI infrastructure repositories and proposes INFRASCOPE, a framework to automatically detect these variants.

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

The paper introduces HRBench, a unified and comprehensive evaluation framework for systematically benchmarking and comparing various thinking-mode switching strategies in hybrid-reasoning LLMs.

CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict

The paper introduces CyberJurors, a multi-agent framework and the VerdictBench benchmark to simulate and solve complex e-commerce dispute verdicts by modeling the reasoning and consensus process of crowdsourced jurors.

Global Policy-Space Response Oracles for Two-Player Zero-Sum Games

The paper introduces Global PSRO, a novel deep reinforcement learning framework that efficiently approximates Nash equilibria in large two-player zero-sum games by intelligently expanding the strategy set using a metric called Population Exploitability.

The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning

The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information is crucial, while semantic details can be unreliable.

VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting

The paper proposes VLBM, a latent basis modeling framework, to achieve state-of-the-art robustness in multivariate time series forecasting, particularly when facing rare but high-impact out-of-distribution (OOD) events.

ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs

This paper proposes ERA, a framework for efficient multimodal large language models using entropy-guided visual token pruning, rectified attention, and bias-aware token recycling.

Mini-Programs, Mega-Problems: Unveiling OAuth-based Authentication Misuses in Mini-Programs via Dynamic Analysis

This paper presents MINIAUTH, the first analysis framework for detecting runtime OAuth-based Authentication (OBA) misuses in mini-programs, discovering 1,834 misuse cases, including critical logic flaws and authentication bypass.

IR275K: A Benchmark for Infrared Multi-Frame Super-Resolution Toward Efficient Remote Sensing

This paper introduces IR275K, a curated benchmark for multi-frame super-resolution in infrared remote sensing, and evaluates CGMamba, a lightweight state-space model, achieving state-of-the-art performance.

Data Pyramid for Embodied Manipulation

This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.CVSurveyRecentJul 27, 2026

Data Pyramid for Embodied Manipulation

Yifan Ye, Yankai Fu, Yaoxu Lv, Bohan Hou +25 more

This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.

View →
cs.CVEmpiricalRecent
Jul 24, 2026

IR275K: A Benchmark for Infrared Multi-Frame Super-Resolution Toward Efficient Remote Sensing

Jie Deng, Heyang Wang, Changxin Wang, Junkai Shen +5 more

This paper introduces IR275K, a curated benchmark for multi-frame super-resolution in infrared remote sensing, and evaluates CGMamba, a lightweight state-space model, achieving state-of-the-art perfor…

View →
cs.CREmpiricalRecentJul 9, 2026

Mini-Programs, Mega-Problems: Unveiling OAuth-based Authentication Misuses in Mini-Programs via Dynamic Analysis

Zidong Zhang, Zhentao Xie, Lingyun Ying, Qinsheng Hou +3 more

This paper presents MINIAUTH, the first analysis framework for detecting runtime OAuth-based Authentication (OBA) misuses in mini-programs, discovering 1,834 misuse cases, including critical logic fla…

View →
cs.CVEmpiricalRecentJun 30, 2026

ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs

Yuhao Wang, Mu Qiao, Haiwen Diao, Yunzhi Zhuge +4 more

This paper proposes ERA, a framework for efficient multimodal large language models using entropy-guided visual token pruning, rectified attention, and bias-aware token recycling.

View →
cs.LGcs.AIRecentJun 1, 2026

VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting

Xudong Zhang, Jierui Lei, Jiacheng Li, Lingdong Shen +2 more

The paper proposes VLBM, a latent basis modeling framework, to achieve state-of-the-art robustness in multivariate time series forecasting, particularly when facing rare but high-impact out-of-distrib…

View →
cs.CLcs.AIRecentMay 29, 2026

The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning

Xudong Zhang, Jian Yang, Shengkai Wang, Jiangpeng Tian +4 more

The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information…

View →
cs.AIRecentMay 27, 2026

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

Yansong Ning, Mianpeng Liu, Jingwen Ye, Weidong Zhang +1 more

The paper introduces HRBench, a unified and comprehensive evaluation framework for systematically benchmarking and comparing various thinking-mode switching strategies in hybrid-reasoning LLMs.

View →
cs.AIcs.SIRecentMay 27, 2026

CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict

Yanhui Sun, Wu Liu, Haifeng Ming, Xinru Wang +2 more

The paper introduces CyberJurors, a multi-agent framework and the VerdictBench benchmark to simulate and solve complex e-commerce dispute verdicts by modeling the reasoning and consensus process of cr…

View →
cs.AIRecentMay 27, 2026

Global Policy-Space Response Oracles for Two-Player Zero-Sum Games

Junyu Zhang, Feihong Yang, Jian Wang, Chao Wang +1 more

The paper introduces Global PSRO, a novel deep reinforcement learning framework that efficiently approximates Nash equilibria in large two-player zero-sum games by intelligently expanding the strategy…

View →
cs.CRRecentMay 19, 2026

Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection

Tian Dong, Yanjun Chen, Shoufeng Zhang, Huaien Zhang +5 more

This paper measures the prevalence of recurring vulnerability patterns (variants) across multiple AI infrastructure repositories and proposes INFRASCOPE, a framework to automatically detect these vari…

View →