Yu-Gang Jiang

VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling

Yuqi Zhang, Cheng Chen, Yuyu Guo +6

Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-attention. Current solutions eit…

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

Junke Wang, Qihang Zhang, Shuai Yang +5

This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers. Existing WAMs typically inherit reconstruction-orient…

DisCo: World Models with Discrete Camera Motion Control

Hongrui Huang, Junke Wang, Quanhao Li +2

Controllable video world models target interactive world exploration, where models must faithfully execute explicit action commands while preserving visual quality and temporal coh…

EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation

Zuhao Ge, Xiaosong Jia, Chao Wu +3

Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into sparse nodes, discarding fin…

CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping

Haoyu Zhao, Jiaxi Gu, Haoran Chen +11

Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly inject numerical camera param…

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval

Zichen Zou, Xiaosong Jia, Zuxuan Wu +1

Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global attention prevents long context…

CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization

Yitong Chen, Zuxuan Wu, Xipeng Qiu +1

Autoregressive (AR) language models rely on causal tokenization, but extending this paradigm to vision remains non-trivial. Current visual tokenizers either flatten 2D patches into…

Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference

Jiaqi Leng, Shuyuan Tu, Haidong Cao +4

Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific fine-tu…

Learning Accurate Segmentation Purely from Self-Supervision

Zuyao You, Zuxuan Wu, Yu-Gang Jiang

Accurately segmenting objects without any manual annotations remains one of the core challenges in computer vision. In this work, we introduce Selfment, a fully self-supervised fra…

DCDM: Divide-and-Conquer Diffusion Models for Consistency-Preserving Video Generation

Haoyu Zhao, Yuang Zhang, Junqi Cheng +5

Recent video generative models have demonstrated impressive visual fidelity, yet they often struggle with semantic, geometric, and identity consistency. In this paper, we propose a…

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention

Xiaosong Jia, Yihang Sun, Junqi You +5

Feedforward models for novel view synthesis (NVS) have recently advanced by transformer-based methods like LVSM, using attention among all input and target views. In this work, we…

Repeating Words for Video-Language Retrieval with Coarse-to-Fine Objectives

Haoyu Zhao, Jiaxi Gu, Shicong Wang +4

The explosive growth of video streaming presents challenges in achieving high accuracy and low training costs for video-language retrieval. However, existing methods rely on large-…

StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation

Shuyuan Tu, Yueming Pan, Yinming Huang +6

Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper present…

Multi-Prompt Progressive Alignment for Multi-Source Unsupervised Domain Adaptation

Haoran Chen, Zexiao Wang, Haidong Cao +2

Large Vision-Language Models like CLIP have become a powerful foundation for Unsupervised Domain Adaptation due to their strong zero-shot generalization. State-of-the-art methods t…

StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image Animation

Shuyuan Tu, Zhen Xing, Xintong Han +5

Current diffusion models for human image animation often struggle to maintain identity (ID) consistency, especially when the reference image and driving video differ significantly…

CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design

Hui Zhang, Dexiang Hong, Maoke Yang +7

Graphic design plays a vital role in visual communication across advertising, marketing, and multimedia entertainment. Prior work has explored automated graphic design generation u…

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL

Junke Wang, Zhi Tian, Xun Wang +4

This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference o…

Enhancing Vision Foundation Models via Multimodal Continual Pre-Training

Yitong Chen, Lingchen Meng, Wujian Peng +4

Vision Foundation Models (VFMs) provide strong visual representations for a wide range of applications. In this work, we enhance prevailing VFMs through multimodal training, allowi…

Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning

Haoran Chen, Ping Wang, Zihan Zhou +3

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted…

Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection

Yitong Chen, Wenhao Yao, Lingchen Meng +3

Enabling models to recognize vast open-world categories has been a longstanding pursuit in object detection. By leveraging the generalization capabilities of vision-language models…

CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

Hui Zhang, Dexiang Hong, Yitong Wang +4

Diffusion models have been recognized for their ability to generate images that are not only visually appealing but also of high artistic quality. As a result, Layout-to-Image (L2I…

INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning

Wujian Peng, Lingchen Meng, Yitong Chen +7

Large Multimodal Models (LMMs) have made significant breakthroughs with the advancement of instruction tuning. However, while existing models can understand images and videos at a…

ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection

Zhihao Sun, Haoran Jiang, Haoran Chen +4

Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When dir…