Author name cluster

Haowei Liu

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.

7 papers

2 author rows

AAAI Conference 2026 Conference Paper

MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation

Run Ling
Ke Cao
Jian Lu
Ao Ma
Haowei Liu
Runze He
Changwei Wang
Rongtao Xu

Multi-subject video generation aims to synthesize videos from textual prompts and multiple reference images, ensuring that each subject preserves natural scale and visual fidelity. However, current methods face two challenges: scale inconsistency, where variations in subject size lead to unnatural generation, and permutation sensitivity, where the order of reference inputs causes subject distortion. In this paper, we propose MoFu, a unified framework that tackles both challenges. For scale inconsistency, we introduce Scale-Aware Modulation (SMO), an LLM-guided module that extracts implicit scale cues from the prompt and modulates features to ensure consistent subject sizes. To address permutation sensitivity, we present a simple yet effective Fourier Fusion strategy that processes the frequency information of reference features via the Fast Fourier Transform to produce a unified representation. Besides, we design a Scale-Permutation Stability Loss to jointly encourage scale-consistent and permutation-invariant generation. To further evaluate these challenges, we establish a dedicated benchmark with controlled variations in subject scale and reference permutation. Extensive experiments demonstrate that MoFu significantly outperforms existing methods in preserving natural scale, subject fidelity, and overall visual quality.

PDF Details DOI

AAAI Conference 2026 Conference Paper

OTI: A Model-free and Visually Interpretable Measure of Image Attackability

Jiaming Liang
Haowei Liu
Chi-Man Pun

Despite the tremendous success of neural networks, benign images can be corrupted by adversarial perturbations to deceive these models. Intriguingly, images differ in their attackability. Specifically, given an attack configuration, some images are easily corrupted, whereas others are more resistant. Evaluating image attackability has important applications in active learning, adversarial training, and attack enhancement. This prompts a growing interest in developing attackability measures. However, existing methods are scarce and suffer from two major limitations: (1) They rely on a model proxy to provide prior knowledge (e.g., gradients or minimal perturbation) to extract model-dependent image features. Unfortunately, in practice, many task-specific models are not readily accessible. (2) Extracted features characterizing image attackability lack visual interpretability, obscuring their direct relationship with the images. To address these, we propose a novel Object Texture Intensity (OTI), a model-free and visually interpretable measure of image attackability, which measures image attackability as the texture intensity of the image's semantic object. Theoretically, we describe the principles of OTI from the perspectives of decision boundaries as well as the mid- and high-frequency characteristics of adversarial perturbations. Comprehensive experiments demonstrate that OTI is effective and computationally efficient. In addition, our OTI provides the adversarial machine learning community with a visual understanding of attackability.

PDF Details DOI

AAAI Conference 2026 Conference Paper

RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation

Run Ling
Wenji Wang
Yuting Liu
Guibing Guo
Haowei Liu
Jian Lu
Quanwei Zhang
Yexing Xu

Personalized image generation is crucial for improving the user experience, as it renders reference images into preferred ones according to user visual preferences. Although effective, existing methods face two main issues. First, existing methods treat all items in the user's historical sequence equally when extracting user preferences, overlooking the varying semantic similarities between historical items and the reference item. Disproportionately high weights for low-similarity items distort user visual preferences for the reference item. Second, existing methods heavily rely on consistency between generated and reference images to optimize generation, which leads to underfitting user preferences and hinders personalization. To address these issues, we propose Retrieval Augmented Personalized Image GenerAtion guided by Recommendation (RAGAR). Our approach uses a retrieval mechanism to assign different weights to historical items according to their similarities to the reference item, thereby extracting more refined users' visual preferences for the reference item. Then we introduce a novel rank task based on the multi-modal ranking model to optimize the personalization of the generated images instead of forcing depend on consistency. Extensive experiments and human evaluations on three real-world datasets demonstrate that RAGAR achieves significant improvements in both personalization and semantic metrics compared to five baselines.

PDF Details DOI

AAAI Conference 2026 Conference Paper

RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers

Ke Cao
Jing Wang
Ao Ma
Jiasong Feng
Xuanhua He
Run Ling
Haowei Liu
Jian Lu

The Diffusion Transformer plays a pivotal role in advancing text-to-image and text-to-video generation, owing primarily to its inherent scalability. However, existing controlled diffusion transformer methods incur significant parameter and computational overheads and suffer from inefficient resource allocation due to their failure to account for the varying relevance of control information across different transformer layers. To address this, we propose the Relevance-Guided Efficient Controllable Generation framework, RelaCtrl, enabling efficient and resource-optimized integration of control signals into the Diffusion Transformer. First, we evaluate the relevance of each layer in the Diffusion Transformer to the control information by assessing the ControlNet Relevance Score, which measures the impact of skipping each control layer on both the quality of generation and the control effectiveness during inference. Based on the strength of the relevance, we then tailor the positioning, parameter scale, and modeling capacity of the control layers to reduce unnecessary parameters and redundant computations. Additionally, to further improve efficiency, we replace the self-attention and FFN in the commonly used copy block with the carefully designed Two-Dimensional Shuffle Mixer (TDSM), enabling efficient implementation of both the token mixer and channel mixer. Both qualitative and quantitative experimental results demonstrate that our approach achieves superior performance with only 15% of the parameters and computational complexity compared to PixArt-delta.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation

Yuyang Wanyan
Xi Zhang
Haiyang Xu
Haowei Liu
Junyang Wang
Jiabo Ye
Yutong Kou
Ming Yan

In recent years, Multimodal Large Language Models (MLLMs) have been extensively utilized for multimodal reasoning tasks, including Graphical User Interface (GUI) automation. Unlike general offline multimodal tasks, GUI automation is executed in online interactive environments, necessitating step-by-step decision-making based on the real-time status of the environment. This task has a lower tolerance for decision-making errors at each step, as any mistakes may cumulatively disrupt the process and potentially lead to irreversible outcomes like deletions or payments. To address these issues, we introduce a pre-operative critic mechanism that provides effective feedback prior to the actual execution, by reasoning about the potential outcome and correctness of actions. Specifically, we propose a Suggestion-aware Group Relative Policy Optimization (S-GRPO) strategy to construct our pre-operative critic model GUI-Critic-R1, incorporating a novel suggestion reward to enhance the reliability of the model's feedback. Furthermore, we develop a reasoning-bootstrapping based data collection pipeline to create a GUI-Critic-Train and a GUI-Critic-Test, filling existing gaps in GUI critic data. Static experiments on the GUI-Critic-Test across both mobile and web domains reveal that our GUI-Critic-R1 offers significant advantages in critic accuracy compared to current MLLMs. Dynamic evaluation on GUI automation benchmark further highlights the effectiveness and superiority of our model, as evidenced by improved success rates and operational efficiency. The code is available at https: //github. com/X-PLUG/MobileAgent/tree/main/GUI-Critic-R1.

PDF Details

ICLR Conference 2025 Conference Paper

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Jiabo Ye
Haiyang Xu 0001
Haowei Liu
Anwen Hu
Ming Yan 0008
Qi Qian 0001
Ji Zhang 0011
Fei Huang 0002

Multi-modal Large Language Models have demonstrated remarkable capabilities in executing instructions for a variety of single-image tasks. Despite this progress, significant challenges remain in modeling long image sequences. In this work, we introduce the versatile multi-modal large language model, mPLUG-Owl3, which enhances the capability for long image-sequence understanding in scenarios that incorporate retrieved image-text knowledge, multimodal in-context examples, and lengthy videos. Specifically, we propose novel hyper attention blocks to efficiently integrate vision and language into a common language-guided semantic space, thereby facilitating the processing of extended multi-image scenarios. We conduct evaluations on 21 benchmarks that cover single/multi-image, and short/long video understanding. mPLUG-Owl3 achieves competitive performance with the state-of-the-art methods while reducing inference time and memory usage by 87.8\% and 48.5\% in average. Moreover, we propose a Distractor Resistance evaluation to assess the ability of models to maintain focus amidst distractions. mPLUG-Owl3 also demonstrates outstanding performance in distractor resistance on ultra-long visual sequence inputs. We hope that mPLUG-Owl3 can contribute to the development of more efficient and powerful multimodal large language models.

Details

ECAI Conference 2025 Conference Paper

Rethinking the Effect of LoRA in Foundation Models for Long-Tailed Recognition

Haowei Liu
Shijia Sun
Liang Chen

Long-tailed recognition (LTR) has seen a surge in the level of attention it receives due to its practical value. Fine-tuning vision-language models (VLMs) has garnered significant attention among the various long-tailed approaches available, with foundation models thriving. While parameter-efficient fine-tuning (PEFT) methods such as adapter and visual prompt tuning (VPT) exhibit strong performance in long-tailed recognition, low-rank adaptation (LoRA), which is prominent in large language models (LLMs), fails to achieve comparable effectiveness in this context. To address the challenge, we introduce LotoRA, a groundbreaking long-tailed low-rank adaptation module. By leveraging diagonal blocks, LotoRA effectively enhances the rank while simultaneously reducing the number of parameters. This innovative approach overcomes the parameter limitations of traditional LoRA, enabling more efficient and targeted learning. Complementing this, we integrate Semantic Attention Pooling into the vision encoder and Semantic Prompt Embedding into the text encoder. These two components synergistically enhance the model’s capacity to represent tail classes by extracting more profound semantic features, effectively addressing the information deficiency often associated with tail categories in long-tailed datasets. Experimental results demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches based on PEFT. Furthermore, our approach provides new insights into parameter-efficient adaptation for long-tailed recognition tasks with foundation models.

Details