79 citations · 244 across the 48 of their papers we have counts for
50 papers
Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration
Xiaolong Shen, Zongxin Yang, Yi Yang
Restoring incomplete or damaged 3D objects is crucial for cultural heritage preservation, occluded object reconstruction, and artistic design. Existing methods primarily focus on g…
EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering
Xiaopeng Yuan, Zebin Wang, Suwen Wang +3
Long-context question answering (QA) remains challenging for smaller language models even when answer-bearing evidence is already present in the input. Existing within-context retr…
MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation
Dewei Zhou, Xinyu Huang, Xun Wang +6
Generative visual models fundamentally struggle with precise spatial control. This arises from a core disconnect: models can process textual descriptions of space but cannot direct…
TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking
Jiyuan Hu, Zechuan Zhang, Zongxin Yang +1
Existing 3D Gaussian Splatting (3DGS) editing methods primarily focus on appearance modification and often struggle to support flexible geometry editing while preserving structural…
Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
Ruisi Zhao, Haoren Zheng, Zongxin Yang +2
Rigged 3D assets are fundamental to 3D deformation and animation. However, existing 3D generation methods face challenges in generating animatable geometry, while rigging technique…
Beyond Independent Genes: Learning Module-Inductive Representations for Single-Cell Gene Perturbation Prediction
Jiafa Ruan, Ruijie Quan, Liyang Xu +2
Predicting transcriptional responses to genetic perturbations is a central problem in functional genomics. In practice, perturbation responses are rarely gene-independent but inste…
Are Image-to-Video Models Good Zero-Shot Image Editors?
Zechuan Zhang, Zhenyuan Chen, Zongxin Yang +1
Large-scale video diffusion models show strong world simulation and temporal reasoning abilities, but their use as zero-shot image editors remains underexplored. We introduce IF-Ed…
BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
Dewei Zhou, Mingwei Li, Zongxin Yang +5
Conditional image generation enhances text-to-image synthesis with structural, spatial, or stylistic priors, but current methods face challenges in handling conflicts between sourc…
Insert Anything: Image Insertion via In-Context Editing in DiT
Wensong Song, Hong Jiang, Zongxing Yang +2
This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexib…
DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models
Dewei Zhou, Mingwei Li, Zongxin Yang +1
Image-conditioned generation methods, such as depth- and canny-conditioned approaches, have demonstrated remarkable abilities for precise image synthesis. However, existing models…
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
Zechuan Zhang, Ji Xie, Yu Lu +2
Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive d…
3D Object Manipulation in a Single Image using Generative Models
Ruisi Zhao, Zechuan Zhang, Zongxin Yang +1
Object manipulation in images aims to not only edit the object's presentation but also gift objects with motion. Previous methods encountered challenges in concurrently handling st…
3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering
Dewei Zhou, Ji Xie, Zongxin Yang +1
The growing demand for controllable outputs in text-to-image generation has driven significant advancements in multi-instance generation (MIG), enabling users to define both instan…
Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data
Chao Liang, Linchao Zhu, Zongxin Yang +2
We focus on the challenging problem of learning an unbiased classifier from a large number of potentially relevant but noisily labeled web images given only a few clean labeled ima…
Origin Identification for Text-Guided Image-to-Image Diffusion Models
Wenhao Wang, Yifan Sun, Zongxin Yang +3
Text-guided image-to-image diffusion models excel in translating images based on textual prompts, allowing for precise and creative visual modifications. However, such a powerful t…
Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation
Kexin Li, Zongxin Yang, Yi Yang +1
Audio-visual video segmentation (AVVS) aims to generate pixel-level maps of sound-producing objects that accurately align with the corresponding audio. However, existing methods of…
3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation
Dewei Zhou, Ji Xie, Zongxin Yang +1
The increasing demand for controllable outputs in text-to-image generation has spurred advancements in multi-instance generation (MIG), allowing users to define both instance layou…
Replication in Visual Diffusion Models: A Survey and Outlook
Wenhao Wang, Yifan Sun, Zongxin Yang +3
Visual diffusion models have revolutionized the field of creative AI, producing high-quality and diverse content. However, they inevitably memorize training images or videos, subse…
MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis
Dewei Zhou, You Li, Fan Ma +2
We introduce the Multi-Instance Generation (MIG) task, which focuses on generating multiple instances within a single image, each accurately placed at predefined positions with att…
MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis
Dewei Zhou, You Li, Fan Ma +2
We present a Multi-Instance Generation (MIG) task, simultaneously generating multiple instances with diverse controls in one image. Given a set of predefined coordinates and their…
IDPro: Flexible Interactive Video Object Segmentation by ID-queried Concurrent Propagation
Kexin Li, Tao Jiang, Zongxin Yang +3
Interactive Video Object Segmentation (iVOS) is a challenging task that requires real-time human-computer interaction. To improve the user experience, it is important to consider t…
DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)
Zongxin Yang, Guikun Chen, Xiaodi Li +2
Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like g…
GD^2-NeRF: Generative Detail Compensation via GAN and Diffusion for One-shot Generalizable Neural Radiance Fields
Xiao Pan, Zongxin Yang, Shuai Bai +1
In this paper, we focus on the One-shot Novel View Synthesis (O-NVS) task which targets synthesizing photo-realistic novel views given only one reference image per scene. Previous…
SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance
Yuanyou Xu, Zongxin Yang, Yi Yang
Powered by large-scale text-to-image generation models, text-to-3D avatar generation has made promising progress. However, most methods fail to produce photorealistic results, limi…