Wenyu Liu

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Kangsheng Duan, Ziyang Xu, Wenyu Liu +3

While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructin…

Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning

Yu Zhu, Yongkang Li, Wenjie Zhu +5

Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (SFT), which often limits reas…

ReWorld: Representation Learning for World Action Models

Tianze Xia, Lijun Zhou, Kaixin Xiong +8

World Action Models (WAMs) unify future environment prediction with action generation for autonomous driving, yet existing approaches optimize only the final outputs, leaving inter…

Cross-Layer Attentive Feature Upsampling for Low-latency Semantic Segmentation

Tianheng Cheng, Xinggang Wang, Junchao Liao +1

Semantic segmentation is a fundamental problem in computer vision and it requires high-resolution feature maps for dense prediction. Current coordinate-guided low-resolution featur…

4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer

Xianfeng Wu, Yajing Bai, Minghan Li +5

Constructing 4D language fields is crucial for embodied AI, augmented/virtual reality, and 4D scene understanding, as they provide enriched semantic representations of dynamic envi…

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

Lunbin Zeng, Jingfeng Yao, Bencheng Liao +3

Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce…

Visual Generation Tuning

Jiahao Guo, Sinan Du, Jingfeng Yao +7

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However…

Gait Recognition via Collaborating Discriminative and Generative Diffusion Models

Haijun Xiong, Bin Feng, Bang Wang +2

Gait recognition offers a non-intrusive biometric solution by identifying individuals through their walking patterns. Although discriminative models have achieved notable success i…

Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

Ya Zou, Jingfeng Yao, Siyuan Yu +3

There is a growing demand for deploying large generative AI models on mobile devices. For recent popular video generative models, however, the Variational AutoEncoder (VAE) represe…

PixelHacker: Image Inpainting with Structural and Semantic Consistency

Ziyang Xu, Kangsheng Duan, Xiaolei Shen +5

Image inpainting is a fundamental research area between image editing and image generation. Recent state-of-the-art (SOTA) methods have explored novel attention mechanisms, lightwe…

STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-to-4D Gaussian Splatting

Yunze Deng, Haijun Xiong, Bin Feng +2

Text-to-4D generation is rapidly developing and widely applied in various scenarios. However, existing methods often fail to incorporate adequate spatio-temporal modeling and promp…

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling

Yingyue Li, Bencheng Liao, Wenyu Liu +1

With the advancement of RNN models with linear complexity, the quadratic complexity challenge of transformers has the potential to be overcome. Notably, the emerging Mamba-2 has de…

GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA Images

Ziyang Xu, Huangxuan Zhao, Wenyu Liu +1

The rapid and accurate direct multi-frame interpolation method for Digital Subtraction Angiography (DSA) images is crucial for reducing radiation and providing real-time assistance…

GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

Haoyi Jiang, Liu Liu, Tianheng Cheng +5

3D Semantic Occupancy Prediction is fundamental for spatial understanding, yet existing approaches face challenges in scalability and generalization due to their reliance on extens…

Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation

Yongkang Li, Tianheng Cheng, Bin Feng +2

Recent open-vocabulary segmentation methods adopt mask generators to predict segmentation masks and leverage pre-trained vision-language models, e.g., CLIP, to classify these masks…

FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification

Jingfeng Yao, Wang Cheng, Wenyu Liu +1

Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training w…

PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification

Bin Hu, Xinggang Wang, Wenyu Liu

Person Re-Identification (ReID) aims to retrieve relevant individuals in non-overlapping camera images and has a wide range of applications in the field of public safety. In recent…