Dong Zhang
10 indexed papers
Research Timeline
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.
The paper introduces HRBench, a unified and comprehensive evaluation framework for systematically benchmarking and comparing various thinking-mode switching strategies in hybrid-reasoning LLMs.
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.
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 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.
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.
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.
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.
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.
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.