Author name cluster

Zhen Han

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

AAAI Conference 2026 Conference Paper

FRBAT: Conditionally-Visible Physical Backdoor Attack via Fluorescence

Yalun Wu
Liu Liu
Endong Tong
Yingxiao Xiang
Xiaoting Lyu
Zhen Han
Jiqiang Liu

Deep neural networks are increasingly vulnerable to physically deployable backdoor attacks, which manipulate real-world objects to induce targeted model failures. However, current physical backdoor attacks predominantly rely on perpetually visible triggers appended to target objects. These methods inevitably expose attack traces during the deployment phase, risking human suspicion prior to activation. In this paper, we propose a conditionally-visible physical backdoor attack, which can only be activated under specific optical conditions and thereby overcomes the risk of being detected after deployment and before the attack. Specifically, to ensure robust and reliable activation, we design irregular polygonal pattern as triggers to against across environmental variations. Moreover, we introduce a dual-phase mechanism (dormant and activated) to enable stealthy deployment. Our trigger remains invisible and dormant under non-attack conditions, leaving no physical traces. It activates instantaneously under specific illumination, inducing the target model to perform the desired behavior. We conduct experiments on traffic sign recognition tasks to compare our attack with six digital and seven physical attacks, and assess its performance against potential defenses. Extensive experimental results demonstrate the effectiveness, stealthiness, and robustness of our attack.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and Dataset

Qifan Liang
Junlin Li
Zhen Han
Xihao Wang
Zhongyuan Wang
Bin Mei

Electrocautery or lasers will inevitably generate surgical smoke, which hinders the visual guidance of laparoscopic videos for surgical procedures. The surgical smoke can be classified into different types based on its motion patterns, leading to distinctive spatio-temporal characteristics across smoky laparoscopic videos. However, existing desmoking methods fail to account for such smoke-type-specific distinctions. Therefore, we propose the first Smoke-Type-Aware Laparoscopic Video Desmoking Network (STANet) by introducing two smoke types: Diffusion Smoke and Ambient Smoke. Specifically, a smoke mask segmentation sub-network is designed to jointly conduct smoke mask and smoke type predictions based on the attention-weighted mask aggregation, while a smokeless video reconstruction sub-network is proposed to perform specially desmoking on smoky features guided by two types of smoke mask. To address the entanglement challenges of two smoke types, we further embed a coarse-to-fine disentanglement module into the mask segmentation sub-network, which yields more accurate disentangled masks through the smoke-type-aware cross attention between non-entangled and entangled regions. In addition, we also construct the first large-scale synthetic video desmoking dataset with smoke type annotations. Extensive experiments demonstrate that our method not only outperforms state-of-the-art approaches in quality evaluations, but also exhibits superior generalization across multiple downstream surgical tasks.

PDF Details DOI

ICLR Conference 2025 Conference Paper

ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer

Zhen Han
Zeyinzi Jiang
Yulin Pan
Jingfeng Zhang
Chaojie Mao
Chen-Wei Xie
Yu Liu 0063
Jingren Zhou 0001

Diffusion models have emerged as a powerful generative technology and have been found to be applicable in various scenarios. Most existing foundational diffusion models are primarily designed for text-guided visual generation and do not support multi-modal conditions, which are essential for many visual editing tasks. This limitation prevents these foundational diffusion models from serving as a unified model in the field of visual generation, like GPT-4 in the natural language processing field. In this work, we propose ACE, an All-round Creator and Editor, which achieves comparable performance compared to those expert models in a wide range of visual generation tasks. To achieve this goal, we first introduce a unified condition format termed Long-context Condition Unit (LCU), and propose a novel Transformer-based diffusion model that uses LCU as input, aiming for joint training across various generation and editing tasks. Furthermore, we propose an efficient data collection approach to address the issue of the absence of available training data. It involves acquiring pairwise images with synthesis-based or clustering-based pipelines and supplying these pairs with accurate textual instructions by leveraging a fine-tuned multi-modal large language model. To comprehensively evaluate the performance of our model, we establish a benchmark of manually annotated pairs data across a variety of visual generation tasks. The extensive experimental results demonstrate the superiority of our model in visual generation fields. Thanks to the all-in-one capabilities of our model, we can easily build a multi-modal chat system that responds to any interactive request for image creation using a single model to serve as the backend, avoiding the cumbersome pipeline typically employed in visual agents.

Details

AAAI Conference 2025 Conference Paper

WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration

Yao Zhang
Zijian Ma
Yunpu Ma
Zhen Han
Yu Wu
Volker Tresp

LLM-based autonomous agents often fail to execute complex web tasks that require dynamic interaction, largely due to the inherent uncertainty and complexity of these environments. Existing LLM-based web agents typically rely on rigid, expert-designed policies specific to certain states and actions, lacking the flexibility and generalizability needed to adapt to unseen tasks. In contrast, humans excel by exploring unknowns, continuously adapting strategies based on new observations, and resolving ambiguities through exploration. To emulate human-like adaptability, web agents need strategic exploration and complex decision-making. Monte Carlo Tree Search (MCTS) is well-suited for this, but classical MCTS struggles with vast action spaces, unpredictable state transitions, and incomplete information in web tasks. In light of this, we develop WebPilot, a multi-agent system with a dual optimization strategy that improves MCTS to better handle complex web environments. Specifically, the Global Optimization phase involves generating a high-level plan by breaking down tasks into manageable subtasks, continuously refining this plan through reflective analysis of new observations and previous subtask attempts, thereby focusing the search process and mitigating challenges posed by vast action spaces in classical MCTS. Subsequently, the Local Optimization phase executes each subtask using a tailored MCTS designed for complex environments, effectively addressing uncertainties and managing incomplete information by iteratively refining decisions based on new observations. Experimental results on WebArena and MiniWoB++ demonstrate the effectiveness of WebPilot. Notably, on WebArena, WebPilot achieves SOTA performance with GPT-4, achieving a 93% relative increase in success rate over the concurrent tree search-based method. WebPilot advances autonomous agents, enabling more reliable decision-making in practical environments.

PDF Details DOI

IROS Conference 2024 Conference Paper

Torque Ripple Reduction in Quasi-Direct Drive Motors Through Angle-Based Repetitive Learning Observer and Model Predictive Torque Controller

Hefei Zhang
Xiaohu Zhang
Jinyu Cheng
Jiangtao Hu
Chao Ji
Yu Wang 0038
Yutong Jiang
Zhen Han

Torque ripple reduction in quasi-direct drive (QDD) motors is crucial in their robotic applications for dynamic locomotion and dexterous manipulation. In this paper, we present a novel approach for reducing torque ripples of QDD motors, which integrates an angle-based repetitive learning observer (ARLO) and a model predictive control-based field-oriented controller (MPC-FOC). The proposed method successfully improves the torque loop control bandwidth and surpasses conventional proportional-integral (PI) controllers owing to the integrated physical constraints inside MPC. Additionally, the ARLO portion is able to mitigate ripple caused by the inherent cogging torque in brushless motors and also the periodic friction torque from the planetary gearboxes in QDD systems. The effectiveness of the proposed method is demonstrated through both simulation of a single QDD motor and experiments on a two-degree-of-freedom robotic leg, where the performance improvement can be 72. 7% in speed tracking and 58. 5% in trajectory tracking. The proposed method shows great potential in facilitating smooth motion and precise force control in future robotic applications.

Details

NeurIPS Conference 2023 Conference Paper

Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models

Shuo Chen
Jindong Gu
Zhen Han
Yunpu Ma
Philip Torr
Volker Tresp

Various adaptation methods, such as LoRA, prompts, and adapters, have been proposed to enhance the performance of pre-trained vision-language models in specific domains. As test samples in real-world applications usually differ from adaptation data, the robustness of these adaptation methods against distribution shifts are essential. In this study, we assess the robustness of 11 widely-used adaptation methods across 4 vision-language datasets under multimodal corruptions. Concretely, we introduce 7 benchmark datasets, including 96 visual and 87 textual corruptions, to investigate the robustness of different adaptation methods, the impact of available adaptation examples, and the influence of trainable parameter size during adaptation. Our analysis reveals that: 1) Adaptation methods are more sensitive to text corruptions than visual corruptions. 2) Full fine-tuning does not consistently provide the highest robustness; instead, adapters can achieve better robustness with comparable clean performance. 3) Contrary to expectations, our findings indicate that increasing the number of adaptation data and parameters does not guarantee enhanced robustness; instead, it results in even lower robustness. We hope this study could benefit future research in the development of robust multimodal adaptation methods. The benchmark, code, and dataset used in this study can be accessed at https: //adarobustness. github. io.

PDF Details