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

Rui Zhang

11 indexed papers

Recent (6 mo)
11
With code
0
Influential cites
0
Benchmarked
0

Publications per year

11
26

Top categories

AI×5Crypto×5NLP×3ML×2Software Eng.×2Vision×1Game Theory×1Algorithms×1

Frequent co-authors

Hongwei Li2×
Guowen Xu2×
XiangRui Zhang2×
Qiang Li2×
Haining Wang2×
Jiarui Zhang1×

Research Timeline

2026
Implicit Patterns in LLM-Based Binary Analysis

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 Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training

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.

Feedback-Driven Execution for LLM-Based Binary Analysis

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.

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study

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.

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection

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: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts

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.

Reconfigurable Antennas for Next-generation Mobile Communication Networks: A Comprehensive Survey and Tutorial

This paper presents a comprehensive survey on reconfigurable antennas for next-generation mobile networks, focusing on their potential and applications.

MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations

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.

Algorithmic Expert Aggregation

This paper studies the problem of aggregating calibrated Bayesian experts into a new calibrated expert.

An Exam for Active Observers

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.

ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning

The paper introduces ToolSciVer, a framework for multimodal scientific claim verification using three type-aware visual tools and GRPO for training.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.CLEmpiricalRecentJul 17, 2026

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.

View →
cs.CLcs.AIEmpirical
Recent
Jul 17, 2026

ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning

Binglin Zhou, Peng Shi, Ryo Kamoi, Nan Zhang +1 more

The paper introduces ToolSciVer, a framework for multimodal scientific claim verification using three type-aware visual tools and GRPO for training.

View →
cs.GTcs.DSTheoreticalRecentJul 9, 2026

Algorithmic Expert Aggregation

Wei Tang, Hanrui Zhang

This paper studies the problem of aggregating calibrated Bayesian experts into a new calibrated expert.

View →
cs.SDcs.AIDatasetRecentJul 8, 2026

MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations

Sirui Zhang, Tianle Wang, Xinyi Tong, Peiyang Yu +7 more

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.

View →
cs.ITSurveyRecentJun 10, 2026

Reconfigurable Antennas for Next-generation Mobile Communication Networks: A Comprehensive Survey and Tutorial

Yizhe Zhao, Long Zhang, Halvin Yang, Kun Yang +3 more

This paper presents a comprehensive survey on reconfigurable antennas for next-generation mobile networks, focusing on their potential and applications.

View →
cs.LGcs.AIRecentMay 30, 2026

CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts

Rui Zhang, Xinle Wu, Yao Lu

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 LL…

View →
cs.CRcs.SERecentMay 5, 2026

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection

Shihao Weng, Yang Feng, Jinrui Zhang, Xiaofei Xie +2 more

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 th…

View →
cs.CRRecentApr 23, 2026

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study

Zihan Wang, Rui Zhang, Yu Liu, Chi Liu +3 more

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 signific…

View →
cs.CRRecentApr 16, 2026

Feedback-Driven Execution for LLM-Based Binary Analysis

XiangRui Zhang, Qiang Li, Haining Wang

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…

View →
cs.CRcs.CLRecentApr 9, 2026

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training

Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen +5 more

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 def…

View →
cs.AIcs.CRcs.SERecentMar 19, 2026

Implicit Patterns in LLM-Based Binary Analysis

Qiang Li, XiangRui Zhang, Haining Wang

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.

View →