11 papers
TextSculptor: Training and Benchmarking Scene Text Editing
Yiheng Lin, Siyu Jiao, Xiaohan Lan +12
Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editi…
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
Aili Chen, Aonian Li, Baichuan Zhou +215
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
VSE-MOT: Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Enhancement
Jun Du, Weiwei Xing, Ming Li +1
Current multi-object tracking (MOT) algorithms typically overlook issues inherent in low-quality videos, leading to significant degradation in tracking performance when confronted…
CDFlow: Generative Gradient Flows for Configuration Space Distance Fields via Neural ODEs
Mengzhu Li, Yunyu Zhou, He Ying +1
Signed Distance Fields (SDFs) are a fundamental representation in robot motion planning. Their configuration-space counterpart, the Configuration Space Distance Field (CDF), direct…
Robust Brain Tumor Segmentation with Incomplete MRI Modalities Using Hölder Divergence and Mutual Information-Enhanced Knowledge Transfer
Runze Cheng, Xihang Qiu, Ming Li +3
Multimodal MRI provides critical complementary information for accurate brain tumor segmentation. However, conventional methods struggle when certain modalities are missing due to…
Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
Zihan Su, Xuerui Qiu, Hongbin Xu +6
The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, inv…
Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking
Ziyi Wang, Songbai Tan, Gang Xu +5
With the success of autoregressive learning in large language models, it has become a dominant approach for text-to-image generation, offering high efficiency and visual quality. H…
PVChat: Personalized Video Chat with One-Shot Learning
Yufei Shi, Weilong Yan, Gang Xu +6
Video large language models (ViLLMs) excel in general video understanding, e.g., recognizing activities like talking and eating, but struggle with identity-aware comprehension, suc…
Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction
Gan Chen, Ying He, Mulin Yu +5
Recent advancements in implicit 3D reconstruction methods, e.g., neural rendering fields and Gaussian splatting, have primarily focused on novel view synthesis of static or dynamic…
EventGPT: Event Stream Understanding with Multimodal Large Language Models
Shaoyu Liu, Jianing Li, Guanghui Zhao +5
Event cameras record visual information as asynchronous pixel change streams, excelling at scene perception under unsatisfactory lighting or high-dynamic conditions. Existing multi…
Uncertainty Quantification via Hölder Divergence for Multi-View Representation Learning
Yan Zhang, Ming Li, Chun Li +3
Evidence-based deep learning represents a burgeoning paradigm for uncertainty estimation, offering reliable predictions with negligible extra computational overheads. Existing meth…