Huaibo Huang

Huaibo Huang, Xiaoqiang Zhou, Jie Cao et al.

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized, which sacrifice the capacity to capture long-range dependency. A challenge then arises: can we access efficient and effective global context modeling at the early stages of a neural network? To address this issue, we draw inspiration from the design of superpixels, which reduces the number of image primitives in subsequent processing, and introduce super tokens into vision transformer. Super tokens attempt to provide a semantically meaningful tessellation of visual content, thus reducing the token number in self-attention as well as preserving global modeling. Specifically, we propose a simple yet strong super token attention (STA) mechanism with three steps: the first samples super tokens from visual tokens via sparse association learning, the second performs self-attention on super tokens, and the last maps them back to the original token space. STA decomposes vanilla global attention into multiplications of a sparse association map and a low-dimensional attention, leading to high efficiency in capturing global dependencies. Based on STA, we develop a hierarchical vision transformer. Extensive experiments demonstrate its strong performance on various vision tasks. In particular, without any extra training data or label, it achieves 86.4% top-1 accuracy on ImageNet-1K with less than 100M parameters. It also achieves 53.9 box AP and 46.8 mask AP on the COCO detection task, and 51.9 mIOU on the ADE20K semantic segmentation task. Code is released at https://github.com/hhb072/STViT.

Qihang Fan, Huaibo Huang, Mingrui Chen et al.

Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity, thereby constraining the applicability of ViT. To alleviate these issues, we draw inspiration from the recent Retentive Network (RetNet) in the field of NLP, and propose RMT, a strong vision backbone with explicit spatial prior for general purposes. Specifically, we extend the RetNet's temporal decay mechanism to the spatial domain, and propose a spatial decay matrix based on the Manhattan distance to introduce the explicit spatial prior to Self-Attention. Additionally, an attention decomposition form that adeptly adapts to explicit spatial prior is proposed, aiming to reduce the computational burden of modeling global information without disrupting the spatial decay matrix. Based on the spatial decay matrix and the attention decomposition form, we can flexibly integrate explicit spatial prior into the vision backbone with linear complexity. Extensive experiments demonstrate that RMT exhibits exceptional performance across various vision tasks. Specifically, without extra training data, RMT achieves **84.8%** and **86.1%** top-1 acc on ImageNet-1k with **27M/4.5GFLOPs** and **96M/18.2GFLOPs**. For downstream tasks, RMT achieves **54.5** box AP and **47.2** mask AP on the COCO detection task, and **52.8** mIoU on the ADE20K semantic segmentation task. Code is available at https://github.com/qhfan/RMT

Qihang Fan, Huaibo Huang, Jiyang Guan et al.

Vision Transformers (ViTs) have been shown to be effective in various vision tasks. However, resizing them to a mobile-friendly size leads to significant performance degradation. Therefore, developing lightweight vision transformers has become a crucial area of research. This paper introduces CloFormer, a lightweight vision transformer that leverages context-aware local enhancement. CloFormer explores the relationship between globally shared weights often used in vanilla convolutional operators and token-specific context-aware weights appearing in attention, then proposes an effective and straightforward module to capture high-frequency local information. In CloFormer, we introduce AttnConv, a convolution operator in attention's style. The proposed AttnConv uses shared weights to aggregate local information and deploys carefully designed context-aware weights to enhance local features. The combination of the AttnConv and vanilla attention which uses pooling to reduce FLOPs in CloFormer enables the model to perceive high-frequency and low-frequency information. Extensive experiments were conducted in image classification, object detection, and semantic segmentation, demonstrating the superiority of CloFormer. The code is available at \url{https://github.com/qhfan/CloFormer}.

Zi Wang, Huaibo Huang, Aihua Zheng et al.

Occluded person re-identification (Re-ID), the task of searching for the same person's images in occluded environments, has attracted lots of attention in the past decades. Recent approaches concentrate on improving performance on occluded data by data/feature augmentation or using extra models to predict occlusions. However, they ignore the imbalance problem in this task and can not fully utilize the information from the training data. To alleviate these two issues, we propose a simple yet effective method with Parallel Augmentation and Dual Enhancement (PADE), which is robust on both occluded and non-occluded data and does not require any auxiliary clues. First, we design a parallel augmentation mechanism (PAM) to generate more suitable occluded data to mitigate the negative effects of unbalanced data. Second, we propose the global and local dual enhancement strategy (DES) to promote the context information and details. Experimental results on three widely used occluded datasets and two non-occluded datasets validate the effectiveness of our method. The code is available at https://github.com/littleprince1121/PADE_Parallel_Augmentation_and_Dual_Enhancement_for_Occluded_Person_ReID

Qihang Fan, Huaibo Huang, Xiaoqiang Zhou et al.

Recent advancements in vision backbones have significantly improved their performance by simultaneously modeling images' local and global contexts. However, the bidirectional interaction between these two contexts has not been well explored and exploited, which is important in the human visual system. This paper proposes a Fully Adaptive Self-Attention (FASA) mechanism for vision transformer to model the local and global information as well as the bidirectional interaction between them in context-aware ways. Specifically, FASA employs self-modulated convolutions to adaptively extract local representation while utilizing self-attention in down-sampled space to extract global representation. Subsequently, it conducts a bidirectional adaptation process between local and global representation to model their interaction. In addition, we introduce a fine-grained downsampling strategy to enhance the down-sampled self-attention mechanism for finer-grained global perception capability. Based on FASA, we develop a family of lightweight vision backbones, Fully Adaptive Transformer (FAT) family. Extensive experiments on multiple vision tasks demonstrate that FAT achieves impressive performance. Notably, FAT accomplishes a 77.6% accuracy on ImageNet-1K using only 4.5M parameters and 0.7G FLOPs, which surpasses the most advanced ConvNets and Transformers with similar model size and computational costs. Moreover, our model exhibits faster speed on modern GPU compared to other models. Code will be available at https://github.com/qhfan/FAT.

Xiaotian Han, Yiren Jian, Xuefeng Hu et al.

Pre-training on large-scale, high-quality datasets is crucial for enhancing the reasoning capabilities of Large Language Models (LLMs), especially in specialized domains such as mathematics. Despite the recognized importance, the Multimodal LLMs (MLLMs) field currently lacks a comprehensive open-source pre-training dataset specifically designed for mathematical reasoning. To address this gap, we introduce InfiMM-WebMath-40B, a high-quality dataset of interleaved image-text documents. It comprises 24 million web pages, 85 million associated image URLs, and 40 billion text tokens, all meticulously extracted and filtered from CommonCrawl. We provide a detailed overview of our data collection and processing pipeline. To demonstrate the robustness of InfiMM-WebMath-40B, we conducted evaluations in both text-only and multimodal settings. Our evaluations on text-only benchmarks show that, despite utilizing only 40 billion tokens, our dataset significantly enhances the performance of our 1.3B model, delivering results comparable to DeepSeekMath-1.3B, which uses 120 billion tokens for the same model size. Nevertheless, with the introduction of our multi-modal math pre-training dataset, our models set a new state-of-the-art among open-source models on multi-modal math benchmarks such as MathVerse and We-Math. We release our data at https://huggingface.co/datasets/Infi-MM/InfiMM-WebMath-40B.

Rui Wang, Peipei Li, Huaibo Huang et al.

We present a novel language-driven ordering alignment method for ordinal classification. The labels in ordinal classification contain additional ordering relations, making them prone to overfitting when relying solely on training data. Recent developments in pre-trained vision-language models inspire us to leverage the rich ordinal priors in human language by converting the original task into a visionlanguage alignment task. Consequently, we propose L2RCLIP, which fully utilizes the language priors from two perspectives. First, we introduce a complementary prompt tuning technique called RankFormer, designed to enhance the ordering relation of original rank prompts. It employs token-level attention with residual-style prompt blending in the word embedding space. Second, to further incorporate language priors, we revisit the approximate bound optimization of vanilla cross-entropy loss and restructure it within the cross-modal embedding space. Consequently, we propose a cross-modal ordinal pairwise loss to refine the CLIP feature space, where texts and images maintain both semantic alignment and ordering alignment. Extensive experiments on three ordinal classification tasks, including facial age estimation, historical color image (HCI) classification, and aesthetic assessment demonstrate its promising performance. The code is available at https://github.com/raywang335/L2RCLIP.

Tingkai Liu, Yunzhe Tao, Haogeng Liu et al.

We present a novel human annotated dataset for evaluating the ability for visual-language models to generate both short and long descriptions for real-world video clips, termed DeVAn (Dense Video Annotation). The dataset contains 8.5K YouTube video clips of 20-60 seconds in duration and covers a wide range of topics and interests. Each video clip is independently annotated by 5 human annotators, producing both captions (1 sentence) and summaries (3-10 sentences). Given any video selected from the dataset and its corresponding ASR information, we evaluate visuallanguage models on either caption or summary generation that is grounded in both the visual and auditory content of the video. Additionally, models are also evaluated on caption- and summary-based retrieval tasks, where the summary-based retrieval task requires the identification of a target video given excerpts of a given summary. Given the novel nature of the paragraph-length video summarization task, we compared different existing evaluation metrics and their alignment with human preferences and found that model-based evaluation metrics provide more semantically-oriented and human-aligned evaluation. Finally, we benchmarked a wide range of current video-language models on DeVAn, and we aim for DeVAn to serve as a useful evaluation set in the age of large language models and complex multi-modal tasks. Code is available at https: //github.com/TK-21st/DeVAn.

Jin Liu, Huaibo Huang, Jie Cao et al.

Diffusion-based text-to-image generation models have significantly advanced the field of art content synthesis. However, current portrait stylization methods generally require either model fine-tuning based on examples or the employment of DDIM Inversion to revert images to noise space, both of which substantially decelerate the image generation process. To overcome these limitations, this paper presents an inversion-free portrait stylization framework based on diffusion models that accomplishes content and style feature fusion in merely four sampling steps. We observed that Latent Consistency Models employing consistency distillation can effectively extract representative Consistency Features from noisy images. To blend the Consistency Features extracted from both content and style images, we introduce a Style Enhancement Attention Control technique that meticulously merges content and style features within the attention space of the target image. Moreover, we propose a feature merging strategy to amalgamate redundant features in Consistency Features, thereby reducing the computational load of attention control. Extensive experiments have validated the effectiveness of our proposed framework in enhancing stylization efficiency and fidelity. The code is available at \url{https://github.com/liujin112/ZePo}.

Yueying Zou, Pei Pei Li, Zekun Li et al.

In recent years, AI-generated videos have become increasingly realistic and sophisticated. Meanwhile, Large Vision-Language Models (LVLMs) have shown strong potential for detecting such content. However, existing evaluation protocols largely treat the task as a binary classification problem and rely on coarse-grained metrics such as overall accuracy, providing limited insight into where LVLMs succeed or fail. To address this limitation, we introduce GenVideoLens, a fine-grained benchmark that enables dimension-wise evaluation of LVLM capabilities in AI-generated video detection. The benchmark contains 400 highly deceptive AI-generated videos and 100 real videos, annotated by experts across 15 authenticity dimensions covering perceptual, optical, physical, and temporal cues. We evaluate eleven representative LVLMs on this benchmark. Our analysis reveals a pronounced dimensional imbalance. While LVLMs perform relatively well on perceptual cues, they struggle with optical consistency, physical interactions, and temporal-causal reasoning. Model performance also varies substantially across dimensions, with smaller open-source models sometimes outperforming stronger proprietary models on specific authenticity cues. Temporal perturbation experiments further show that current LVLMs make limited use of temporal information. Overall, GenVideoLens provides diagnostic insights into LVLM behavior, revealing key capability gaps and offering guidance for improving future AI-generated video detection systems.

Shihao Li, Huaibo Huang, Junxian Duan et al.

Multi-modal object Re-IDentification (ReID) aims to obtain complete identity features across heterogeneous modalities. However, most existing methods rely on implicit feature fusion modules, making it difficult to model fine-grained recognition patterns under various challenges in real world. Benefiting from the powerful Multi-modal Large Language Models (MLLMs), the object appearances are effectively translated into descriptive captions. In this paper, we propose a reliable caption generation pipeline based on attribute confidence, which significantly reduces the unknown recognition rate of MLLMs and improves the quality of generated text. Additionally, to model diverse identity patterns, we propose a novel ReID framework, named NEXT, the Multi-grained Mixture of Experts via Text-Modulation for Multi-modal Object Re-Identification. Specifically, we decouple the recognition problem into semantic and structural branches to separately capture fine-grained appearance features and coarsegrained structure features. For semantic recognition, we first propose a Text-Modulated Semantic Experts (TMSE), which randomly samples high-quality captions to modulate experts capturing semantic features and mining inter-modality complementary cues. Second, to recognize structure features, we propose a Context-Shared Structure Experts (CSSE), which focuses on the holistic object structure and maintains identity structural consistency via a soft routing mechanism. Finally, we propose a Multi-Grained Features Aggregation (MGFA), which adopts a unified fusion strategy to effectively integrate multi-grained expert features into the final identity representations. Extensive experiments on two public person datasets and three vehicle datasets demonstrate the effectiveness of our method, showing that it significantly outperforms existing state-of-the-art methods.

Peipei Li, Rui Wang, Huaibo Huang et al.

Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input. Most existing methods often produce one deterministic estimation. This paper proposes a novel CLIP-driven Pluralistic Aging Diffusion Autoencoder (PADA) to enhance the diversity of aging patterns. First, we employ diffusion models to generate diverse low-level aging details via a sequential denoising reverse process. Second, we present Probabilistic Aging Embedding (PAE) to capture diverse high-level aging patterns, which represents age information as probabilistic distributions in the common CLIP latent space. A text-guided KL-divergence loss is designed to guide this learning. Our method can achieve pluralistic face aging conditioned on open-world aging texts and arbitrary unseen face images. Qualitative and quantitative experiments demonstrate that our method can generate more diverse and high-quality plausible aging results.

Haogeng Liu, Qihang Fan, Tingkai Liu et al.

This paper proposes Video-Teller, a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment to significantly enhance the video-to-text generation task. Video-Teller boosts the training efficiency by utilizing frozen pretrained vision and language modules. It capitalizes on the robust linguistic capabilities of large language models, enabling the generation of both concise and elaborate video descriptions. To effectively integrate visual and auditory information, Video-Teller builds upon the image-based BLIP-2 model and introduces a cascaded Q-Former which fuses information across frames and ASR texts. To better guide video summarization, we introduce a fine-grained modality alignment objective, where the cascaded Q-Former's output embedding is trained to align with the caption/summary embedding created by a pretrained text auto-encoder. Experimental results demonstrate the efficacy of our proposed video-language foundation model in accurately comprehending videos and generating coherent and precise language descriptions. It is worth noting that the fine-grained alignment enhances the model's capabilities (4% improvement of CIDEr score on MSR-VTT) with only 13% extra parameters in training and zero additional cost in inference.

Yuang Ai, Xiaoqiang Zhou, Huaibo Huang et al.

Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) by accessing both the source and target data. Considering privacy policies or transmission restrictions of source data in practical scenarios, we propose a SOurce-free Domain Adaptation framework for image SR (SODA-SR) to address this issue, i.e., adapt a source-trained model to a target domain with only unlabeled target data. SODA-SR leverages the source-trained model to generate refined pseudo-labels for teacher-student learning. To better utilize pseudo-labels, we propose a novel wavelet-based augmentation method, named Wavelet Augmentation Transformer (WAT), which can be flexibly incorporated with existing networks, to implicitly produce useful augmented data. WAT learns low-frequency information of varying levels across diverse samples, which is aggregated efficiently via deformable attention. Furthermore, an uncertainty-aware self-training mechanism is proposed to improve the accuracy of pseudo-labels, with inaccurate predictions being rectified by uncertainty estimation. To acquire better SR results and avoid overfitting pseudo-labels, several regularization losses are proposed to constrain target LR and SR images in the frequency domain. Experiments show that without accessing source data, SODA-SR outperforms state-of-the-art UDA methods in both synthetic$\rightarrow$real and real$\rightarrow$real adaptation settings, and is not constrained by specific network architectures.

Siyu Xing, Jie Cao, Huaibo Huang et al.

Flow matching as a paradigm of generative model achieves notable success across various domains. However, existing methods use either multi-round training or knowledge within minibatches, posing challenges in finding a favorable coupling strategy for straightening trajectories to few-step generation. To address this issue, we propose a novel approach, Straighter trajectories of Flow Matching (StraightFM). It straightens trajectories with the coupling strategy from the entire distribution level. More specifically, during training, StraightFM creates couplings of images and noise via one diffusion model as a coupling prior to straighten trajectories for few-step generation. Our coupling strategy can also integrate with the existing coupling direction from real data to noise, improving image quality in few-step generation. Experimental results on pixel space and latent space show that StraightFM yields attractive samples within 5 steps. Moreover, our unconditional StraightFM is seamlessly compatible with training-free multimodal conditional generation, maintaining high-quality image generation in few steps.

Purui Bai, Tao Wu, Jiayang Sun et al.

The rapid progress of Large Language Models (LLMs) has spurred growing interest in Multi-modal LLMs (MLLMs) and motivated the development of benchmarks to evaluate their perceptual and comprehension abilities. Existing benchmarks, however, are limited to static images or single videos, overlooking the complex interactions across multiple videos. To address this gap, we introduce the Multi-Video Perception Evaluation Benchmark (MVPBench), a new benchmark featuring 14 subtasks across diverse visual domains designed to evaluate models on extracting relevant information from video sequences to make informed decisions. MVPBench includes 5K question-answering tests involving 2.7K video clips sourced from existing datasets and manually annotated clips. Extensive evaluations reveal that current models struggle to process multi-video inputs effectively, underscoring substantial limitations in their multi-video comprehension. We anticipate MVPBench will drive advancements in multi-video perception.

Lixia Ma, Puning Yang, Yuting Xu et al.

Currently, the rapid development of computer vision and deep learning has enabled the creation or manipulation of high-fidelity facial images and videos via deep generative approaches. This technology, also known as deepfake, has achieved dramatic progress and become increasingly popular in social media. However, the technology can generate threats to personal privacy and national security by spreading misinformation. To diminish the risks of deepfake, it is desirable to develop powerful forgery detection methods to distinguish fake faces from real faces. This paper presents a comprehensive survey of recent deep learning-based approaches for facial forgery detection. We attempt to provide the reader with a deeper understanding of the current advances as well as the major challenges for deepfake detection based on deep learning. We present an overview of deepfake techniques and analyse the characteristics of various deepfake datasets. We then provide a systematic review of different categories of deepfake detection and state-of-the-art deepfake detection methods. The drawbacks of existing detection methods are analyzed, and future research directions are discussed to address the challenges in improving both the performance and generalization of deepfake detection.

Mingrui Chen, Hexiong Yang, Haogeng Liu et al.

In this paper, we present a holistic multimodal benchmark that evaluates the reasoning capabilities of MLLMs with an explicit focus on reasoning width, a complementary dimension to the more commonly studied reasoning depth. Specifically, reasoning depth measures the model's ability to carry out long-chain, sequential reasoning in which each step is tightly and rigorously linked to the next. Reasoning width tends to focus more on the model's capacity for broad trial-and-error search or multi-constrained optimization: it must systematically traverse many possible and parallelized reasoning paths, apply diverse constraints to prune unpromising branches, and identify valid solution routes for efficient iteration or backtracking. To achieve it, we carefully curate 1200+ high-quality multimodal cases spanning heterogeneous domains, and propose a fine-grained tree-of-thought evaluation protocol that jointly quantifies reasoning width and depth. We evaluate 12 major model families (over 30 advanced MLLMs) across difficulty tiers, question types, and required skills. Results show that while current models exhibit strong performance on general or common-sense VQA tasks, they still struggle to combine deep sequential thought chains with wide exploratory search to perform genuine insight-based reasoning. Finally, we analyze characteristic failure modes to provide possible directions for building MLLMs that reason not only deeper but also wider.

Shiran Ge, Chenyi Huang, Yuang Ai et al.

Group Relative Policy Optimization (GRPO) is a powerful technique for aligning generative models, but its effectiveness is bottlenecked by the conflict between large group sizes and prohibitive computational costs. In this work, we investigate the trade-off through empirical studies, yielding two key observations. First, we discover the reward clustering phenomenon in which many trajectories collapse toward the group-mean reward, offering limited optimization value. Second, we design a heuristic strategy named Optimal Variance Filtering (OVF), and verify that a high-variance subset of trajectories, selected by OVF can outperform the larger, unfiltered group. However, this static, post-sampling OVF approach still necessitates critical computational overhead, as it performs unnecessary sampling for trajectories that are ultimately discarded. To resolve this, we propose Pro-GRPO (Proactive GRPO), a novel dynamic framework that integrates latent feature-based trajectory pruning into the sampling process. Through the early termination of reward-clustered trajectories, Pro-GRPO reduces computational overhead. Leveraging its efficiency, Pro-GRPO employs an "Expand-and-Prune" strategy. This strategy first expands the size of initial sampling group to maximize trajectory diversity, then it applies multi-step OVF to the latents, avoiding prohibitive computational costs. Extensive experiments on both diffusion-based and flow-based models demonstrate the generality and effectiveness of our Pro-GRPO framework.

Hongbo Wang, Huaibo Huang, Pin Wang et al.

Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalignment between isotropic objectives and the intrinsic natural image manifold. While Direct Preference Optimization offers a path to alignment, its reliance on spectrally flat Gaussian noise fails to distinguish authentic high-frequency details from hallucinations. To bridge this geometric gap, we propose ASASR, a theoretically grounded framework that recasts the generative flow into a Sobolev-induced Riemannian geometry by explicitly coloring the noise transition kernel to mirror natural spectral decay. Driving this geometric alignment, we integrate a parametric adversary grounded in the Riesz Representation Theorem, which synthesizes targeted negative samples equivalent to worst-case Sobolev gradients to direct optimization along the tangent space of plausible structural failures. Extensive evaluations demonstrate that ASASR outperforms leading generative baselines, particularly in preserving spectral consistency and structural fidelity, offering a robust solution that effectively mitigates artifacts.

Xing Cui, Zekun Li, Pei Pei Li et al.

Stylized text-to-image generation focuses on creating images from textual descriptions while adhering to a style specified by a few reference images. However, subtle style variations within different reference images can hinder the model from accurately learning the target style. In this paper, we propose InstaStyle, a novel approach that excels in generating high-fidelity stylized images with only a single reference image. Our approach is based on the finding that the inversion noise from a stylized reference image inherently carries the style signal, as evidenced by their non-zero signal-to-noise ratio. We employ DDIM inversion to extract this noise from the reference image and leverage a diffusion model to generate new stylized images from the "style" noise. Additionally, the inherent ambiguity and bias of textual prompts impede the precise conveying of style. To address this, we introduce a learnable style token via prompt refinement, which enhances the accuracy of the style description for the reference image. Qualitative and quantitative experimental results demonstrate that InstaStyle achieves superior performance compared to current benchmarks. Furthermore, our approach also showcases its capability in the creative task of style combination with mixed inversion noise.

Kerui Li, Zhe Jing, Xiaofeng Wang et al.

Inverse Dynamics Models (IDMs) map visual observations to low-level action commands, serving as central components for data labeling and policy execution in embodied AI. However, their performance degrades severely under manipulator truncation, a common failure mode that makes state recovery ill-posed and leads to unstable control. We present StableIDM, a spatio-temporal framework that refines features from visual inputs to stabilize action predictions under such partial observability. StableIDM integrates three complementary components: (1) auxiliary robot-centric masking to suppress background clutter, (2) Directional Feature Aggregation (DFA) for geometry-aware spatial reasoning, which extracts anisotropic features along directions inferred from the visible arm and (3) Temporal Dynamics Refinement (TDR) to smooth and correct predictions via motion continuity. Extensive evaluations validate our approach: StableIDM improves strict action accuracy by 12.1% under severe truncation on the AgiBot benchmark, and increases average task success by 9.7% in real-robot replay. Moreover, it boosts end-to-end grasp success by 11.5% when decoding video-generated plans, and improves downstream VLA real-robot success by 17.6% when functioning as an automatic annotator. These results demonstrate that StableIDM provides a robust and scalable backbone for both policy execution and data generation in embodied artificial intelligence.

Chao Jin, Wenkui Yang, Hao Sun et al.

While progress in GUI agents has been largely driven by industrial-scale training, ungrounded hallucinations often trigger cascading failures in real-world deployments.Unlike general VLM domains, the GUI agent field lacks a hallucination-focused suite for fine-grained diagnosis, reliable evaluation, and targeted mitigation.To bridge this gap, we introduce HalluClear, a comprehensive suite for hallucination mitigation in GUI agents as a complement to computation-intensive scaling. HalluClear comprises: (1) a GUI-specific hallucination taxonomy derived from empirical failure analysis; (2) a calibrated three-stage evaluation workflow which enhances VLM-as-a-judge reliability via expert-annotated benchmarking and ensemble credibility estimation; and (3) a mitigation scheme based on closed-loop structured reasoning, enabling lightweight continual post-training with cold-start initialization for both generalist and GUI-specialist agents. Experiments across representative agents and public benchmarks demonstrate that post-training on only 9K samples within our suite can significantly reduce hallucinations, thereby improving grounding and action fidelity, offering a compute-efficient pathway to robust GUI automation.

Wenkui Yang, Chao Jin, Haisu Zhu et al.

Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger safety alignment. To study robustness under a more practical threat model, we propose Semantic-level UI Element Injection, a red-teaming setting that overlays safety-aligned and harmless UI elements onto screenshots to misdirect the agent's visual grounding. Our method uses a modular Editor-Overlapper-Victim pipeline and an iterative search procedure that samples multiple candidate edits, keeps the best cumulative overlay, and adapts future prompt strategies based on previous failures. Across five victim models, our optimized attacks improve attack success rate by up to 4.4x over random injection on the strongest victims. Moreover, elements optimized on one source model transfer effectively to other target models, indicating model-agnostic vulnerabilities. After the first successful attack, the victim still clicks the attacker-controlled element in more than 15% of later independent trials, versus below 1% for random injection, showing that the injected element acts as a persistent attractor rather than simple visual clutter.

Yuang Ai, Xiaoqiang Zhou, Huaibo Huang et al.

Image restoration (IR) in real-world scenarios presents significant challenges due to the lack of high-capacity models and comprehensive datasets. To tackle these issues, we present a dual strategy: GenIR, an innovative data curation pipeline, and DreamClear, a cutting-edge Diffusion Transformer (DiT)-based image restoration model. GenIR, our pioneering contribution, is a dual-prompt learning pipeline that overcomes the limitations of existing datasets, which typically comprise only a few thousand images and thus offer limited generalizability for larger models. GenIR streamlines the process into three stages: image-text pair construction, dual-prompt based fine-tuning, and data generation & filtering. This approach circumvents the laborious data crawling process, ensuring copyright compliance and providing a cost-effective, privacy-safe solution for IR dataset construction. The result is a large-scale dataset of one million high-quality images. Our second contribution, DreamClear, is a DiT-based image restoration model. It utilizes the generative priors of text-to-image (T2I) diffusion models and the robust perceptual capabilities of multi-modal large language models (MLLMs) to achieve photorealistic restoration. To boost the model's adaptability to diverse real-world degradations, we introduce the Mixture of Adaptive Modulator (MoAM). It employs token-wise degradation priors to dynamically integrate various restoration experts, thereby expanding the range of degradations the model can address. Our exhaustive experiments confirm DreamClear's superior performance, underlining the efficacy of our dual strategy for real-world image restoration. Code and pre-trained models are available at: https://github.com/shallowdream204/DreamClear.

Xuannan Liu, Xing Cui, Peipei Li et al.

The rapid evolution of multimodal foundation models has led to significant advancements in cross-modal understanding and generation across diverse modalities, including text, images, audio, and video. However, these models remain susceptible to jailbreak attacks, which can bypass built-in safety mechanisms and induce the production of potentially harmful content. Consequently, understanding the methods of jailbreak attacks and existing defense mechanisms is essential to ensure the safe deployment of multimodal generative models in real-world scenarios, particularly in security-sensitive applications. To provide comprehensive insight into this topic, this survey reviews jailbreak and defense in multimodal generative models. First, given the generalized lifecycle of multimodal jailbreak, we systematically explore attacks and corresponding defense strategies across four levels: input, encoder, generator, and output. Based on this analysis, we present a detailed taxonomy of attack methods, defense mechanisms, and evaluation frameworks specific to multimodal generative models. Additionally, we cover a wide range of input-output configurations, including modalities such as Any-to-Text, Any-to-Vision, and Any-to-Any within generative systems. Finally, we highlight current research challenges and propose potential directions for future research. The open-source repository corresponding to this work can be found at https://github.com/liuxuannan/Awesome-Multimodal-Jailbreak.

Qihang Fan, Huaibo Huang, Mingrui Chen et al.

In recent years, the Vision Transformer (ViT) has garnered significant attention within the computer vision community. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and suffers from quadratic computational complexity, limiting its applicability. To address these issues, we have proposed RMT, a robust vision backbone with explicit spatial priors for general purposes. RMT utilizes Manhattan distance decay to introduce spatial information and employs a horizontal and vertical decomposition attention method to model global information. Building on the strengths of RMT, Euclidean enhanced Vision Transformer (EVT) is an expanded version that incorporates several key improvements. Firstly, EVT uses a more reasonable Euclidean distance decay to enhance the modeling of spatial information, allowing for a more accurate representation of spatial relationships compared to the Manhattan distance used in RMT. Secondly, EVT abandons the decomposed attention mechanism featured in RMT and instead adopts a simpler spatially-independent grouping approach, providing the model with greater flexibility in controlling the number of tokens within each group. By addressing these modifications, EVT offers a more sophisticated and adaptable approach to incorporating spatial priors into the Self-Attention mechanism, thus overcoming some of the limitations associated with RMT and further enhancing its applicability in various computer vision tasks. Extensive experiments on Image Classification, Object Detection, Instance Segmentation, and Semantic Segmentation demonstrate that EVT exhibits exceptional performance. Without additional training data, EVT achieves 86.6% top1-acc on ImageNet-1k.

Haogeng Liu, Quanzeng You, Xiaotian Han et al.

Multimodal Large Language Models (MLLMs) have experienced significant advancements recently. Nevertheless, challenges persist in the accurate recognition and comprehension of intricate details within high-resolution images. Despite being indispensable for the development of robust MLLMs, this area remains underinvestigated. To tackle this challenge, our work introduces InfiMM-HD, a novel architecture specifically designed for processing images of different resolutions with low computational overhead. This innovation facilitates the enlargement of MLLMs to higher-resolution capabilities. InfiMM-HD incorporates a cross-attention module and visual windows to reduce computation costs. By integrating this architectural design with a four-stage training pipeline, our model attains improved visual perception efficiently and cost-effectively. Empirical study underscores the robustness and effectiveness of InfiMM-HD, opening new avenues for exploration in related areas. Codes and models can be found at https://huggingface.co/Infi-MM/infimm-hd

Qihang Fan, Huaibo Huang, Ran He

The Softmax attention mechanism in Transformer models is notoriously computationally expensive, particularly due to its quadratic complexity, posing significant challenges in vision applications. In contrast, linear attention provides a far more efficient solution by reducing the complexity to linear levels. However, compared to Softmax attention, linear attention often experiences significant performance degradation. Our experiments indicate that this performance drop is due to the low-rank nature of linear attention's feature map, which hinders its ability to adequately model complex spatial information. In this paper, to break the low-rank dilemma of linear attention, we conduct rank analysis from two perspectives: the KV buffer and the output features. Consequently, we introduce Rank-Augmented Linear Attention (RALA), which rivals the performance of Softmax attention while maintaining linear complexity and high efficiency. Based on RALA, we construct the Rank-Augmented Vision Linear Transformer (RAVLT). Extensive experiments demonstrate that RAVLT achieves excellent performance across various vision tasks. Specifically, without using any additional labels, data, or supervision during training, RAVLT achieves an 84.4% Top-1 accuracy on ImageNet-1k with only 26M parameters and 4.6G FLOPs. This result significantly surpasses previous linear attention mechanisms, fully illustrating the potential of RALA. Code will be available at https://github.com/qhfan/RALA.

Yuang Ai, Huaibo Huang, Ran He

Prompt-based all-in-one image restoration (IR) frameworks have achieved remarkable performance by incorporating degradation-specific information into prompt modules. Nevertheless, handling the complex and diverse degradations encountered in real-world scenarios remains a significant challenge. To tackle this, we propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. Specifically, LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. In the pre-training stage, we enhance the pre-trained CLIP model by introducing a simple mechanism that scales it to higher resolutions, allowing us to extract robust degradation representations that adaptively guide the IR network. In the fine-tuning stage, we refine the pre-trained IR network through low-rank adaptation (LoRA). Built upon a Mixture-of-Experts (MoE) architecture, LoRA-IR dynamically integrates multiple low-rank restoration experts through a degradation-guided router. This dynamic integration mechanism significantly enhances our model's adaptability to diverse and unknown degradations in complex real-world scenarios. Extensive experiments demonstrate that LoRA-IR achieves SOTA performance across 14 IR tasks and 29 benchmarks, while maintaining computational efficiency. Code and pre-trained models will be available at: https://github.com/shallowdream204/LoRA-IR.

Qihang Fan, Huaibo Huang, Zhiying Wu et al.

Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. While various sparse attention mechanisms have been explored, they typically suffer from either significant search latency or insufficient sparsity. In this paper, we propose FlashPrefill, a framework enabling ultra-fast prefilling via instantaneous pattern discovery and thresholding. FlashPrefill leverages a fast block-searching technique to simultaneously locate dynamic vertical, slash, and block-sparse attention patterns. Crucially, it introduces a dynamic thresholding mechanism that bypasses the prohibitive overhead of sorting or accumulating attention scores while effectively eliminating the long-tail distribution to enhance sparsity. Extensive evaluations demonstrate that FlashPrefill achieves a substantial leap in efficiency, delivering an unprecedented 27.78x speedup on 256K sequences. Notably, unlike existing methods that incur efficiency degradation on shorter contexts, FlashPrefill maintains a 1.71x speedup even at a 4K context length, demonstrating its robustness and practical utility across varying sequence scales.

Qihang Fan, Huaibo Huang, Yuang Ai et al.

As the core operator of Transformers, Softmax Attention exhibits excellent global modeling capabilities. However, its quadratic complexity limits its applicability to vision tasks. In contrast, Linear Attention shares a similar formulation with Softmax Attention while achieving linear complexity, enabling efficient global information modeling. Nevertheless, Linear Attention suffers from a significant performance degradation compared to standard Softmax Attention. In this paper, we analyze the underlying causes of this issue based on the formulation of Linear Attention. We find that, unlike Softmax Attention, Linear Attention entirely disregards the magnitude information of the Query. This prevents the attention score distribution from dynamically adapting as the Query scales. As a result, despite its structural similarity to Softmax Attention, Linear Attention exhibits a significantly different attention score distribution. Based on this observation, we propose Magnitude-Aware Linear Attention (MALA), which modifies the computation of Linear Attention to fully incorporate the Query's magnitude. This adjustment allows MALA to generate an attention score distribution that closely resembles Softmax Attention while exhibiting a more well-balanced structure. We evaluate the effectiveness of MALA on multiple tasks, including image classification, object detection, instance segmentation, semantic segmentation, natural language processing, speech recognition, and image generation. Our MALA achieves strong results on all of these tasks. Code will be available at https://github.com/qhfan/MALA

Purui Bai, Junxian Duan, Pin Wang et al.

Although diffusion-based real-world image restoration (Real-IR) has achieved remarkable progress, efficiently leveraging ultra-large-scale pre-trained text-to-image (T2I) models and fully exploiting their potential remain significant challenges. To address this issue, we propose ResFlow-Tuner, an image restoration framework based on the state-of-the-art flow matching model, FLUX.1-dev, which integrates unified multi-modal fusion (UMMF) with test-time scaling (TTS) to achieve unprecedented restoration performance. Our approach fully leverages the advantages of the Multi-Modal Diffusion Transformer (MM-DiT) architecture by encoding multi-modal conditions into a unified sequence that guides the synthesis of high-quality images. Furthermore, we introduce a training-free test-time scaling paradigm tailored for image restoration. During inference, this technique dynamically steers the denoising direction through feedback from a reward model (RM), thereby achieving significant performance gains with controllable computational overhead. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple standard benchmarks. This work not only validates the powerful capabilities of the flow matching model in low-level vision tasks but, more importantly, proposes a novel and efficient inference-time scaling paradigm suitable for large pre-trained models.

Yuang Ai, Jiaming Han, Shaobin Zhuang et al.

We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets each token represent up to $2^{256}$ states, yielding a compact yet highly expressive discrete representation. Sampling from such a huge token space is difficult with standard classification. To resolve this, BitDance uses a binary diffusion head: instead of predicting an index with softmax, it employs continuous-space diffusion to generate the binary tokens. Furthermore, we propose next-patch diffusion, a new decoding method that predicts multiple tokens in parallel with high accuracy, greatly speeding up inference. On ImageNet 256x256, BitDance achieves an FID of 1.24, the best among AR models. With next-patch diffusion, BitDance beats state-of-the-art parallel AR models that use 1.4B parameters, while using 5.4x fewer parameters (260M) and achieving 8.7x speedup. For text-to-image generation, BitDance trains on large-scale multimodal tokens and generates high-resolution, photorealistic images efficiently, showing strong performance and favorable scaling. When generating 1024x1024 images, BitDance achieves a speedup of over 30x compared to prior AR models. We release code and models to facilitate further research on AR foundation models. Code and models are available at: https://github.com/shallowdream204/BitDance.

Shaobin Zhuang, Yuang Ai, Jiaming Han et al.

Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations that carry meaning jointly. This one-token bottleneck limits both the expressiveness of the model during pre-training and its throughput at inference time. Existing remedies such as speculative decoding or diffusion-based language models either leave the underlying bottleneck intact or sacrifice the causal structure essential to language modeling. We propose BitLM, a language model that represents each token as a fixed-length binary code and employs a lightweight diffusion head to denoise multiple tokens in parallel within each block. Crucially, BitLM preserves left-to-right causal attention across blocks while making joint lexical decisions within each block, combining the reliability of autoregressive modeling with the parallelism of iterative refinement. By replacing the large-vocabulary softmax with bitwise denoising, BitLM reframes token generation as iterative commitment in a compact binary space, enabling more efficient pre-training and substantially faster inference without altering the causal foundation that makes language models effective. Our results demonstrate that the one-token-at-a-time paradigm is not a fundamental requirement but an interface choice, and that changing it can yield a stronger and faster language model. We hope BitLM points toward a promising direction for next-generation language model architectures.

Jin Liu, Huaibo Huang, Chao Jin et al.

Face stylization refers to the transformation of a face into a specific portrait style. However, current methods require the use of example-based adaptation approaches to fine-tune pre-trained generative models so that they demand lots of time and storage space and fail to achieve detailed style transformation. This paper proposes a training-free face stylization framework, named Portrait Diffusion. This framework leverages off-the-shelf text-to-image diffusion models, eliminating the need for fine-tuning specific examples. Specifically, the content and style images are first inverted into latent codes. Then, during image reconstruction using the corresponding latent code, the content and style features in the attention space are delicately blended through a modified self-attention operation called Style Attention Control. Additionally, a Chain-of-Painting method is proposed for the gradual redrawing of unsatisfactory areas from rough adjustments to fine-tuning. Extensive experiments validate the effectiveness of our Portrait Diffusion method and demonstrate the superiority of Chain-of-Painting in achieving precise face stylization. Code will be released at \url{https://github.com/liujin112/PortraitDiffusion}.

Chaoyou Fu, Xiang Wu, Yibo Hu et al.

Heterogeneous Face Recognition (HFR) is a challenging issue because of the large domain discrepancy and a lack of heterogeneous data. This paper considers HFR as a dual generation problem, and proposes a novel Dual Variational Generation (DVG) framework. It generates large-scale new paired heterogeneous images with the same identity from noise, for the sake of reducing the domain gap of HFR. Specifically, we first introduce a dual variational autoencoder to represent a joint distribution of paired heterogeneous images. Then, in order to ensure the identity consistency of the generated paired heterogeneous images, we impose a distribution alignment in the latent space and a pairwise identity preserving in the image space. Moreover, the HFR network reduces the domain discrepancy by constraining the pairwise feature distances between the generated paired heterogeneous images. Extensive experiments on four HFR databases show that our method can significantly improve state-of-the-art results. The related code is available at https://github.com/BradyFU/DVG.

Qihang Fan, Huaibo Huang, Zhiying Wu et al.

As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the inference efficiency of long-context processing, several novel low-complexity hybrid architectures have recently been proposed, effectively alleviating the computational burden of long-context inference. However, existing research on long-context prefill acceleration remains predominantly focused on sparse attention mechanisms, which achieve their maximum speedup only on full-attention models. When transferred to emerging architectures--such as linear/full attention hybrids or sliding window/full attention hybrids--these prefill acceleration approaches suffer significant performance degradation. Furthermore, such methods are generally incompatible with continuous batching, making them difficult to integrate into modern inference engines such as vLLM. To this end, we propose UniPrefill, a prefill acceleration framework applicable to virtually any model architecture, which directly accelerates the model's computation at the token level. We further implement UniPrefill as a continuous batching operator and extend vLLM's scheduling strategy to natively support prefill-decode co-processing and tensor parallel for UniPrefill, enabling its seamless integration into vLLM. UniPrefill achieves up to 2.1x speedup in Time-To-First-Token (TTFT), with the acceleration becoming increasingly pronounced as the number of concurrent requests grows.

Xuannan Liu, Peipei Li, Huaibo Huang et al.

The massive generation of multimodal fake news involving both text and images exhibits substantial distribution discrepancies, prompting the need for generalized detectors. However, the insulated nature of training restricts the capability of classical detectors to obtain open-world facts. While Large Vision-Language Models (LVLMs) have encoded rich world knowledge, they are not inherently tailored for combating fake news and struggle to comprehend local forgery details. In this paper, we propose FKA-Owl, a novel framework that leverages forgery-specific knowledge to augment LVLMs, enabling them to reason about manipulations effectively. The augmented forgery-specific knowledge includes semantic correlation between text and images, and artifact trace in image manipulation. To inject these two kinds of knowledge into the LVLM, we design two specialized modules to establish their representations, respectively. The encoded knowledge embeddings are then incorporated into LVLMs. Extensive experiments on the public benchmark demonstrate that FKA-Owl achieves superior cross-domain performance compared to previous methods. Code is publicly available at https://liuxuannan.github.io/FKA_Owl.github.io/.

Yuang Ai, Huaibo Huang, Xiaoqiang Zhou et al.

Despite substantial progress, all-in-one image restoration (IR) grapples with persistent challenges in handling intricate real-world degradations. This paper introduces MPerceiver: a novel multimodal prompt learning approach that harnesses Stable Diffusion (SD) priors to enhance adaptiveness, generalizability and fidelity for all-in-one image restoration. Specifically, we develop a dual-branch module to master two types of SD prompts: textual for holistic representation and visual for multiscale detail representation. Both prompts are dynamically adjusted by degradation predictions from the CLIP image encoder, enabling adaptive responses to diverse unknown degradations. Moreover, a plug-in detail refinement module improves restoration fidelity via direct encoder-to-decoder information transformation. To assess our method, MPerceiver is trained on 9 tasks for all-in-one IR and outperforms state-of-the-art task-specific methods across most tasks. Post multitask pre-training, MPerceiver attains a generalized representation in low-level vision, exhibiting remarkable zero-shot and few-shot capabilities in unseen tasks. Extensive experiments on 16 IR tasks underscore the superiority of MPerceiver in terms of adaptiveness, generalizability and fidelity.

Qihang Fan, Quanzeng You, Xiaotian Han et al.

This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from those seen during training. Our work introduces two key innovations to address this issue. Firstly, we propose a novel module for dynamic resolution adjustment, designed with a single Transformer block, specifically to achieve highly efficient incremental token integration. Secondly, we introduce fuzzy positional encoding in the Vision Transformer to provide consistent positional awareness across multiple resolutions, thereby preventing overfitting to any single training resolution. Our resulting model, ViTAR (Vision Transformer with Any Resolution), demonstrates impressive adaptability, achieving 83.3\% top-1 accuracy at a 1120x1120 resolution and 80.4\% accuracy at a 4032x4032 resolution, all while reducing computational costs. ViTAR also shows strong performance in downstream tasks such as instance and semantic segmentation and can easily combined with self-supervised learning techniques like Masked AutoEncoder. Our work provides a cost-effective solution for enhancing the resolution scalability of ViTs, paving the way for more versatile and efficient high-resolution image processing.

Yuguang Zhang, Qihang Fan, Huaibo Huang

In recent years, Transformers have achieved remarkable progress in computer vision tasks. However, their global modeling often comes with substantial computational overhead, in stark contrast to the human eye's efficient information processing. Inspired by the human eye's sparse scanning mechanism, we propose a \textbf{S}parse \textbf{S}can \textbf{S}elf-\textbf{A}ttention mechanism ($\rm{S}^3\rm{A}$). This mechanism predefines a series of Anchors of Interest for each token and employs local attention to efficiently model the spatial information around these anchors, avoiding redundant global modeling and excessive focus on local information. This approach mirrors the human eye's functionality and significantly reduces the computational load of vision models. Building on $\rm{S}^3\rm{A}$, we introduce the \textbf{S}parse \textbf{S}can \textbf{Vi}sion \textbf{T}ransformer (SSViT). Extensive experiments demonstrate the outstanding performance of SSViT across a variety of tasks. Specifically, on ImageNet classification, without additional supervision or training data, SSViT achieves top-1 accuracies of \textbf{84.4\%/85.7\%} with \textbf{4.4G/18.2G} FLOPs. SSViT also excels in downstream tasks such as object detection, instance segmentation, and semantic segmentation. Its robustness is further validated across diverse datasets.

Mingrui Chen, Haogeng Liu, Hao Liang et al.

In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reasoning. Our exploration mainly comprises of following three perspective: First, through offline data curation, we analyze the U-shaped difficulty distribution of two given datasets using the base model by multi-round sampling, and then filter out prompts that are either too simple or extremely difficult to provide meaningful gradients and perform subsequent two-stage training. Second, we implement an online advantage differentiation, computing group-wise empirical accuracy as a difficulty proxy to adaptively reweight advantages estimation, providing stronger learning signals for more challenging problems. Finally, we introduce difficulty hints as explicit prompts for more complex samples in the second training stage, encouraging the model to calibrate its reasoning depth and perform reflective validation checks. Our comprehensive approach demonstrates significant performances across various multi-modal mathematical reasoning benchmarks with only 2K+0.6K two-stage training data.

Yueying Zou, Peipei Li, Zekun Li et al.

The proliferation of AI-generated media poses significant challenges to information authenticity and social trust, making reliable detection methods highly demanded. Methods for detecting AI-generated media have evolved rapidly, paralleling the advancement of Multimodal Large Language Models (MLLMs). Current detection approaches can be categorized into two main groups: Non-MLLM-based and MLLM-based methods. The former employs high-precision, domain-specific detectors powered by deep learning techniques, while the latter utilizes general-purpose detectors based on MLLMs that integrate authenticity verification, explainability, and localization capabilities. Despite significant progress in this field, there remains a gap in literature regarding a comprehensive survey that examines the transition from domain-specific to general-purpose detection methods. This paper addresses this gap by providing a systematic review of both approaches, analyzing them from single-modal and multi-modal perspectives. We present a detailed comparative analysis of these categories, examining their methodological similarities and differences. Through this analysis, we explore potential hybrid approaches and identify key challenges in forgery detection, providing direction for future research. Additionally, as MLLMs become increasingly prevalent in detection tasks, ethical and security considerations have emerged as critical global concerns. We examine the regulatory landscape surrounding Generative AI (GenAI) across various jurisdictions, offering valuable insights for researchers and practitioners in this field.

Xuannan Liu, Zekun Li, Zheqi He et al.

The increasing deployment of Large Vision-Language Models (LVLMs) raises safety concerns under potential malicious inputs. However, existing multimodal safety evaluations primarily focus on model vulnerabilities exposed by static image inputs, ignoring the temporal dynamics of video that may induce distinct safety risks. To bridge this gap, we introduce Video-SafetyBench, the first comprehensive benchmark designed to evaluate the safety of LVLMs under video-text attacks. It comprises 2,264 video-text pairs spanning 48 fine-grained unsafe categories, each pairing a synthesized video with either a harmful query, which contains explicit malice, or a benign query, which appears harmless but triggers harmful behavior when interpreted alongside the video. To generate semantically accurate videos for safety evaluation, we design a controllable pipeline that decomposes video semantics into subject images (what is shown) and motion text (how it moves), which jointly guide the synthesis of query-relevant videos. To effectively evaluate uncertain or borderline harmful outputs, we propose RJScore, a novel LLM-based metric that incorporates the confidence of judge models and human-aligned decision threshold calibration. Extensive experiments show that benign-query video composition achieves average attack success rates of 67.2%, revealing consistent vulnerabilities to video-induced attacks. We believe Video-SafetyBench will catalyze future research into video-based safety evaluation and defense strategies.

Yuang Ai, Huaibo Huang, Tao Wu et al.

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this issue with sparse or window-based attention, yet inherently limit global context modeling. Linear attention, a variant of softmax attention, demonstrates promise in global context modeling while maintaining linear complexity, offering a potential solution to the above challenge. Despite its efficiency benefits, vanilla linear attention suffers from a significant performance drop in IR, largely due to the low-rank nature of its attention map. To counter this, we propose Rank Enhanced Linear Attention (RELA), a simple yet effective method that enriches feature representations by integrating a lightweight depthwise convolution. Building upon RELA, we propose an efficient and effective image restoration Transformer, named LAformer. LAformer achieves effective global perception by integrating linear attention and channel attention, while also enhancing local fitting capabilities through a convolutional gated feed-forward network. Notably, LAformer eliminates hardware-inefficient operations such as softmax and window shifting, enabling efficient processing of high-resolution images. Extensive experiments across 7 IR tasks and 21 benchmarks demonstrate that LAformer outperforms SOTA methods and offers significant computational advantages.

Qihang Fan, Huaibo Huang, Mingrui Chen et al.

The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens for self-attention, reducing computational requirements. Nonetheless, this strategy neglects semantic information in tokens, possibly scattering semantically-linked tokens across distinct groups, thus compromising the efficacy of self-attention intended for modeling inter-token dependencies. Motivated by these insights, we introduce a fast and balanced clustering method, named Semantic Equitable Clustering (SEC). SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner. In contrast to traditional clustering methods requiring multiple iterations, our method achieves token clustering in a single pass. Additionally, SEC regulates the number of tokens per cluster, ensuring a balanced distribution for effective parallel processing on current computational platforms without necessitating further optimization. Capitalizing on SEC, we propose a versatile vision backbone, SECViT. Comprehensive experiments in image classification, object detection, instance segmentation, and semantic segmentation validate the effectiveness of SECViT. Moreover, SEC can be conveniently and swiftly applied to multimodal large language models (MLLM), such as LLaVA, to serve as a vision language connector, effectively accelerating the model's efficiency while maintaining unchanged or better performance.

Nan Gao, Jia Li, Huaibo Huang et al.

Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of data degradation patterns. Current BFR methods have realized certain restored productions but with inherent neural degradations that limit real-world generalization in complicated scenarios. In this paper, we propose a plug-and-play framework InfoBFR to tackle neural degradations, e.g., prior bias, topological distortion, textural distortion, and artifact residues, which achieves high-generalization face restoration in diverse wild and heterogeneous scenes. Specifically, based on the results from pre-trained BFR models, InfoBFR considers information compression using manifold information bottleneck (MIB) and information compensation with efficient diffusion LoRA to conduct information optimization. InfoBFR effectively synthesizes high-fidelity faces without attribute and identity distortions. Comprehensive experimental results demonstrate the superiority of InfoBFR over state-of-the-art GAN-based and diffusion-based BFR methods, with around 70ms consumption, 16M trainable parameters, and nearly 85% BFR-boosting. It is promising that InfoBFR will be the first plug-and-play restorer universally employed by diverse BFR models to conquer neural degradations.

Nan Gao, Jia Li, Huaibo Huang et al.

Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of degradation patterns. Current methods have low generalization across photorealistic and heterogeneous domains. In this paper, we propose a Diffusion-Information-Diffusion (DID) framework to tackle diffusion manifold hallucination correction (DiffMAC), which achieves high-generalization face restoration in diverse degraded scenes and heterogeneous domains. Specifically, the first diffusion stage aligns the restored face with spatial feature embedding of the low-quality face based on AdaIN, which synthesizes degradation-removal results but with uncontrollable artifacts for some hard cases. Based on Stage I, Stage II considers information compression using manifold information bottleneck (MIB) and finetunes the first diffusion model to improve facial fidelity. DiffMAC effectively fights against blind degradation patterns and synthesizes high-quality faces with attribute and identity consistencies. Experimental results demonstrate the superiority of DiffMAC over state-of-the-art methods, with a high degree of generalization in real-world and heterogeneous settings. The source code and models will be public.

Shaobin Zhuang, Yuang Ai, Jiaming Han et al.

Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generative suitability. However, existing visual tokenizers typically struggle to satisfy these conflicting objectives within a single framework. In this paper, we introduce UniWeTok, a unified discrete tokenizer designed to bridge this gap using a massive binary codebook ($\mathit{2^{128}}$). For training framework, we introduce Pre-Post Distillation and a Generative-Aware Prior to enhance the semantic extraction and generative prior of the discrete tokens. In terms of model architecture, we propose a convolution-attention hybrid architecture with the SigLu activation function. SigLu activation not only bounds the encoder output and stabilizes the semantic distillation process but also effectively addresses the optimization conflict between token entropy loss and commitment loss. We further propose a three-stage training framework designed to enhance UniWeTok's adaptability cross various image resolutions and perception-sensitive scenarios, such as those involving human faces and textual content. On ImageNet, UniWeTok achieves state-of-the-art image generation performance (FID: UniWeTok 1.38 vs. REPA 1.42) while requiring a remarkably low training compute (Training Tokens: UniWeTok 33B vs. REPA 262B). On general-domain, UniWeTok demonstrates highly competitive capabilities across a broad range of tasks, including multimodal understanding, image generation (DPG Score: UniWeTok 86.63 vs. FLUX.1 [Dev] 83.84), and editing (GEdit Overall Score: UniWeTok 5.09 vs. OmniGen 5.06). We release code and models to facilitate community exploration of unified tokenizer and MLLM.