Rui Zhang
11 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper analyzes large-scale reasoning traces from LLM-based binary vulnerability analysis, identifying four structured, token-level implicit patterns that govern how LLMs explore code paths.
The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and defense mechanisms.
The paper introduces FORGE, a feedback-driven execution system that improves LLM-based binary analysis by interleaving reasoning and tool interaction, achieving high-quality vulnerability discovery on complex firmware binaries.
This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a significant and often overlooked copyright risk.
The paper introduces ARGUS, a defense mechanism that uses provenance-aware decision auditing to protect LLM agents from sophisticated, context-aware prompt injection attacks, significantly reducing the attack success rate.
CARE-RL introduces a framework combining protocol-aware reward generation and capability-aware optimization to effectively mitigate cross-domain conflicts in multi-domain reinforcement learning for LLMs.
This paper presents a comprehensive survey on reconfigurable antennas for next-generation mobile networks, focusing on their potential and applications.
The paper introduces MADB, a large-scale dataset and benchmark for music aesthetic assessment with 9,999 tracks annotated by 30 trained annotators across 10 perceptual dimensions.
This paper studies the problem of aggregating calibrated Bayesian experts into a new calibrated expert.
The paper introduces ActiveVision, a benchmark to measure active observation in multimodal large language models, and shows that current models lack robust active visual perception.
The paper introduces ToolSciVer, a framework for multimodal scientific claim verification using three type-aware visual tools and GRPO for training.
Papers
An Exam for Active Observers
Jiarui Zhang, Muzi Tao, Shangshang Wang, Ollie Liu +2 more
The paper introduces ActiveVision, a benchmark to measure active observation in multimodal large language models, and shows that current models lack robust active visual perception.