120 citations · 163 across the 18 of their papers we have counts for
18 papers
CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
Penghui Yang, Long Xing, Xiaoyi Dong +10
Image and video captioning are fundamental tasks that bridge the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Curren…
Qwen3-VL Technical Report
Shuai Bai, Yuxuan Cai, Ruizhe Chen +61
We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively…
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
Long Xing, Xiaoyi Dong, Yuhang Zang +6
Image captioning is a fundamental task that bridges the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-o…
ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
Long Xing, Qidong Huang, Xiaoyi Dong +10
This paper presents ScaleCap, an inference-time scalable image captioning strategy that generates comprehensive and detailed image captions. The key challenges of high-quality imag…
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Yujie Zhou, Jiazi Bu, Pengyang Ling +10
Recent advancements in image relighting models, driven by large-scale datasets and pre-trained diffusion models, have enabled the imposition of consistent lighting. However, video…
MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation
Haochen Xue, Feilong Tang, Ming Hu +13
Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, th…
Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate
Qidong Huang, Xiaoyi Dong, Pan Zhang +6
We present the Modality Integration Rate (MIR), an effective, robust, and generalized metric to indicate the multi-modal pre-training quality of Large Vision Language Models (LVLMs…
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Long Xing, Qidong Huang, Xiaoyi Dong +8
In large vision-language models (LVLMs), images serve as inputs that carry a wealth of information. As the idiom "A picture is worth a thousand words" implies, representing a singl…
SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models
Feifei Wang, Zhentao Tan, Tianyi Wei +2
Despite the success of diffusion-based customization methods on visual content creation, increasing concerns have been raised about such techniques from both privacy and political…
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
Qidong Huang, Xiaoyi Dong, Pan Zhang +6
Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. Existing…
Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting
Qidong Huang, Xiaoyi Dong, Dongdong Chen +5
In this paper, we investigate the adversarial robustness of vision transformers that are equipped with BERT pretraining (e.g., BEiT, MAE). A surprising observation is that MAE has…
Diversity-Aware Meta Visual Prompting
Qidong Huang, Xiaoyi Dong, Dongdong Chen +4
We present Diversity-Aware Meta Visual Prompting~(DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone.…
Hierarchical Terrain Attention and Multi-Scale Rainfall Guidance For Flood Image Prediction
Feifei Wang, Yong Wang, Bing Li +2
With the deterioration of climate, the phenomenon of rain-induced flooding has become frequent. To mitigate its impact, recent works adopt convolutional neural network or its varia…
Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion
Kui Zhang, Hang Zhou, Jie Zhang +3
Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoi…
PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition
Qidong Huang, Xiaoyi Dong, Dongdong Chen +5
Notwithstanding the prominent performance achieved in various applications, point cloud recognition models have often suffered from natural corruptions and adversarial perturbation…
Shape-invariant 3D Adversarial Point Clouds
Qidong Huang, Xiaoyi Dong, Dongdong Chen +3
Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations. Previous adversarial attacks on 3D point cloud recognition have often been crit…
Initiative Defense against Facial Manipulation
Qidong Huang, Jie Zhang, Wenbo Zhou +2
Benefiting from the development of generative adversarial networks (GAN), facial manipulation has achieved significant progress in both academia and industry recently. It inspires…
Poison Ink: Robust and Invisible Backdoor Attack
Jie Zhang, Dongdong Chen, Qidong Huang +5
Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attack, data poisoning attack and backdoor attack. Among them, backdoor…