20 papers
Von Neumann Type Inequalities for NC Operator Balls
Ran Kiri
We establish finite-dimensional von Neumann type inequalities for commuting matrix tuples in noncommutative operator balls. Let be the NC operator ball of a linear…
A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation
Yabin Zhang, Chong Wang, Yunhe Gao +19
Chest X-rays (CXRs) are among the most frequently performed imaging examinations worldwide, yet rising imaging volumes increase radiologist workload and the risk of diagnostic erro…
The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
Hongyuan Liu, Qinli Yang, Wen Li +6
Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the m…
Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models
Yulin Luo, Hao Chen, Zhuangzhe Wu +10
Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately int…
Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs
Yiren Zheng, Shibo Li, Jiaming Liu +2
Current multimodal approaches predominantly treat visual generation as an external process, relying on pixel rendering or code execution, thereby overlooking the native visual repr…
Learning Generalizable 3D Medical Image Representations from Mask-Guided Self-Supervision
Yunhe Gao, Yabin Zhang, Chong Wang +5
Foundation models have transformed vision and language by learning general-purpose representations from large-scale unlabeled data, yet 3D medical imaging lacks analogous approache…
Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge
Jiaming Liu, Felix Petersen, Yunhe Gao +6
Adversarial diffusion and diffusion-inversion methods have advanced unpaired image-to-image translation, but each faces key limitations. Adversarial approaches require target-domai…
Loom: Diffusion-Transformer for Interleaved Generation
Mingcheng Ye, Jiaming Liu, Yiren Song
Interleaved text-image generation aims to jointly produce coherent visual frames and aligned textual descriptions within a single sequence, enabling tasks such as style transfer, c…
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Yubo Huang, Hailong Guo, Fangtai Wu +9
Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon dr…
SpinalSAM-R1: A Vision-Language Multimodal Interactive System for Spine CT Segmentation
Jiaming Liu, Dingwei Fan, Junyong Zhao +3
The anatomical structure segmentation of the spine and adjacent structures from computed tomography (CT) images is a key step for spinal disease diagnosis and treatment. However, t…
MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning
Liujian Tang, Shaokang Dong, Yijia Huang +21
This paper presents MagicGUI, a foundational mobile GUI agent designed to address critical challenges in perception, grounding, and reasoning within real-world mobile GUI environme…
Awesome-OL: An Extensible Toolkit for Online Learning
Zeyi Liu, Songqiao Hu, Pengyu Han +2
In recent years, online learning has attracted increasing attention due to its adaptive capability to process streaming and non-stationary data. To facilitate algorithm development…
Stable-Hair v2: Real-World Hair Transfer via Multiple-View Diffusion Model
Kuiyuan Sun, Yuxuan Zhang, Jichao Zhang +4
While diffusion-based methods have shown impressive capabilities in capturing diverse and complex hairstyles, their ability to generate consistent and high-quality multi-view outpu…
WordCon: Word-level Typography Control in Scene Text Rendering
Wenda Shi, Yiren Song, Zihan Rao +3
Achieving precise word-level typography control within generated images remains a persistent challenge. To address it, we newly construct a word-level controlled scene text dataset…
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
Yuxuan Zhang, Yirui Yuan, Yiren Song +2
Recent advancements in Unet-based diffusion models, such as ControlNet and IP-Adapter, have introduced effective spatial and subject control mechanisms. However, the DiT (Diffusion…
PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data
Shijie Huang, Yiren Song, Yuxuan Zhang +4
We introduce PhotoDoodle, a novel image editing framework designed to facilitate photo doodling by enabling artists to overlay decorative elements onto photographs. Photo doodling…
Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation
Yiren Song, Shengtao Lou, Xiaokang Liu +4
Diffusion models have revolutionized generative modeling with their exceptional ability to produce high-fidelity images. However, misuse of such potent tools can lead to the creati…
FonTS: Text Rendering with Typography and Style Controls
Wenda Shi, Yiren Song, Dengming Zhang +2
Visual text rendering are widespread in various real-world applications, requiring careful font selection and typographic choices. Recent progress in diffusion transformer (DiT)-ba…
ProcessPainter: Learn Painting Process from Sequence Data
Yiren Song, Shijie Huang, Chen Yao +5
The painting process of artists is inherently stepwise and varies significantly among different painters and styles. Generating detailed, step-by-step painting processes is essenti…
Stable-Hair: Real-World Hair Transfer via Diffusion Model
Yuxuan Zhang, Qing Zhang, Yiren Song +3
Current hair transfer methods struggle to handle diverse and intricate hairstyles, limiting their applicability in real-world scenarios. In this paper, we propose a novel diffusion…