Gengyuan Zhang

25 papers A* 3A 3Journal 14Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data Interaction. CoRR Gengyuan Zhang, Tanveer Hannan, Hermine Kleiner, Beste Aydemir, Xinyu Xie, Jian Lan, Thomas Seidl, Volker Tresp, Jindong Gu
2025	A	`conf`	CL-Cross VQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering. WACV Yao Zhang, Haokun Chen, Ahmed Frikha, Denis Krompass, Gengyuan Zhang, Jindong Gu, Volker Tresp
2025	A*	`conf`	FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models. CVPR Haokun Chen, Hang Li, Yao Zhang, Jinhe Bi, Gengyuan Zhang, Yueqi Zhang, Philip Torr, Jindong Gu, Denis Krompass, Volker Tresp
2025	A*	`conf`	Localizing Events in Videos with Multimodal Queries. CVPR Gengyuan Zhang, Mang Ling Ada Fok, Jialu Ma, Yan Xia, Daniel Cremers, Philip Torr, Volker Tresp, Jindong Gu
2025	J	`jnl`	Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs. CoRR Gengyuan Zhang, Mingcong Ding, Tong Liu, Yao Zhang, Volker Tresp
2025	—	`conf`	Modular Integration Optimization of SSVEP for UGV Control. ROBIO Gengyuan Zhang, Duanling Li, Tongchuan Xia, Junwei Zhang
2025	—	`conf`	Multimodal Pragmatic Jailbreak on Text-to-image Models. ACL (1) Tong Liu, Zhixin Lai, Jiawen Wang, Gengyuan Zhang, Shuo Chen, Philip Torr, Vera Demberg, Volker Tresp, Jindong Gu
2025	J	`jnl`	My Answer Is NOT 'Fair': Mitigating Social Bias in Vision-Language Models via Fair and Biased Residuals. CoRR Jian Lan, Yifei Fu, Udo Schlegel, Gengyuan Zhang, Tanveer Hannan, Haokun Chen, Thomas Seidl
2025	A	`conf`	Perceive. Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries. WACV Roberto Amoroso, Gengyuan Zhang, Rajat Koner, Lorenzo Baraldi, Rita Cucchiara, Volker Tresp
2025	J	`jnl`	ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay. CoRR Gengyuan Zhang, Mingcong Ding, Jingpei Wu, Ruotong Liao, Volker Tresp
2024	A	`conf`	Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning. WACV Gengyuan Zhang, Yurui Zhang, Kerui Zhang, Volker Tresp
2024	J	`jnl`	FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models. CoRR Haokun Chen, Hang Li, Yao Zhang, Gengyuan Zhang, Jinhe Bi, Philip Torr, Jindong Gu, Denis Krompass, Volker Tresp
2024	J	`jnl`	Localizing Events in Videos with Multimodal Queries. CoRR Gengyuan Zhang, Mang Ling Ada Fok, Yan Xia, Yansong Tang, Daniel Cremers, Philip Torr, Volker Tresp, Jindong Gu
2024	J	`jnl`	Multimodal Pragmatic Jailbreak on Text-to-image Models. CoRR Tong Liu, Zhixin Lai, Gengyuan Zhang, Philip Torr, Vera Demberg, Volker Tresp, Jindong Gu
2024	J	`jnl`	Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries. CoRR Roberto Amoroso, Gengyuan Zhang, Rajat Koner, Lorenzo Baraldi, Rita Cucchiara, Volker Tresp
2024	—	`conf`	RPF-ELD: Regional Prior Fusion using Early and Late Distillation for Breast Cancer Recognition in Ultrasound Images. BIBM Haosen Wang, Gengyuan Zhang, Yingnan Zhao, Fang Lai, Wenwei Cui, Jiexiao Xue, Qihang Wang, Hao Zhang, Yi Lin
2024	—	`conf`	VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs. EMNLP (Findings) Ruotong Liao, Max Erler, Huiyu Wang, Guangyao Zhai, Gengyuan Zhang, Yunpu Ma, Volker Tresp
2024	J	`jnl`	VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs. CoRR Ruotong Liao, Max Erler, Huiyu Wang, Guangyao Zhai, Gengyuan Zhang, Yunpu Ma, Volker Tresp
2023	J	`jnl`	A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models. CoRR Jindong Gu, Zhen Han, Shuo Chen, Ahmad Beirami, Bailan He, Gengyuan Zhang, Ruotong Liao, Yao Qin, Volker Tresp, Philip H. S. Torr
2023	J	`jnl`	Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning. CoRR Gengyuan Zhang, Yurui Zhang, Kerui Zhang, Volker Tresp
2023	A*	`conf`	Multi-event Video-Text Retrieval. ICCV Gengyuan Zhang, Jisen Ren, Jindong Gu, Volker Tresp
2023	J	`jnl`	Multi-event Video-Text Retrieval. CoRR Gengyuan Zhang, Jisen Ren, Jindong Gu, Volker Tresp
2023	J	`jnl`	SPOT! Revisiting Video-Language Models for Event Understanding. CoRR Gengyuan Zhang, Jinhe Bi, Jindong Gu, Volker Tresp
2022	J	`jnl`	CL-CrossVQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering. CoRR Yao Zhang, Haokun Chen, Ahmed Frikha, Yezi Yang, Denis Krompass, Gengyuan Zhang, Jindong Gu, Volker Tresp
2021	—	`conf`	Time-dependent Entity Embedding is not All You Need: A Re-evaluation of Temporal Knowledge Graph Completion Models under a Unified Framework. EMNLP (1) Zhen Han, Gengyuan Zhang, Yunpu Ma, Volker Tresp

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.