19 citations · 38 across the 56 of their papers we have counts for
59 papers
Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers
Yumiao Li, Peixin Liu, Donglin Di +2
Assessing the impacts of social policy changes is a widely acknowledged challenge for policymakers. Econometric methods can be unreliable when extrapolating to hypothetical scenari…
ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection
Ningning Han, Lei Fan, Jia Guo +5
The deployment of Industrial Anomaly Detection (IAD) in real-world manufacturing frequently encounters a challenging cold-start bottleneck, in which limited normal samples fail to…
Decoupled Vision-Language System for Multimodal Understanding and Generation
Yifan Xu, Baochen Xiong, Xiaoshan Yang +3
We introduce a new architecture design for multimodal large language models (MLLMs), Libra, capable of both multimodal understanding and generation. Libra architecture contains one…
MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving
Zhijing Cheng, Xuancheng Zhang, Donglin Di +4
End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a compact context and a downs…
CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning
He Feng, Yongjia Ma, Donglin Di +2
Portrait animation methods have achieved substantial visual quality and lip synchronization, but fine-grained manipulation of the eye region still faces a trade-off between input g…
Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation
Jintao Sun, Gangyi Ding, Donglin Di +2
Vision-Language Models have achieved strong progress in ground-view visual understanding, yet they remain brittle in high-altitude Unmanned Aerial Vehicle scenes, where objects are…
ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors
Haodong Yu, Yabo Zhang, Donglin Di +2
While diffusion models excel at generating images with conventional dimensions, pushing them to synthesize ultra-high-resolution imagery at extreme aspect ratios (EAR) often trigge…
GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction
Chao Xu, Xiaochen Zhao, Xiang Deng +4
Reconstructing photorealistic and animatable 4D head avatars from a single portrait image remains a fundamental challenge in computer vision. While diffusion models have enabled re…
MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer
Juntong Fang, Zequn Chen, Weiqi Zhang +4
Reconstructing dynamic 4D scenes remains challenging due to the presence of moving objects that corrupt camera pose estimation. Existing optimization methods alleviate this issue w…
Chain of World: World Model Thinking in Latent Motion
Fuxiang Yang, Donglin Di, Lulu Tang +6
Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynami…
FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model
Zhou Liu, Tonghua Su, Hongshi Zhang +4
Advances in image tampering techniques, particularly generative models, pose significant challenges to media verification, digital forensics, and public trust. Existing image forge…
Visual Prompt-Agnostic Evolution
Junze Wang, Lei Fan, Dezheng Zhang +5
Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer…
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
Baorui Ma, Jiahui Yang, Donglin Di +5
Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camer…
EverybodyDance: Bipartite Graph-Based Identity Correspondence for Multi-Character Animation
Haotian Ling, Zequn Chen, Qiuying Chen +6
Consistent pose-driven character animation has achieved remarkable progress in single-character scenarios. However, extending these advances to multi-character settings is non-triv…
EFDiT: Efficient Fine-grained Image Generation Using Diffusion Transformer Models
Kun Wang, Donglin Di, Tonghua Su +1
Diffusion models are highly regarded for their controllability and the diversity of images they generate. However, class-conditional generation methods based on diffusion models of…
Cross-Stain Contrastive Learning for Paired Immunohistochemistry and Histopathology Slide Representation Learning
Yizhi Zhang, Lei Fan, Zhulin Tao +4
Universal, transferable whole-slide image (WSI) representations are central to computational pathology. Incorporating multiple markers (e.g., immunohistochemistry, IHC) alongside H…
Global-Local Aware Scene Text Editing
Fuxiang Yang, Tonghua Su, Donglin Di +4
Scene Text Editing (STE) involves replacing text in a scene image with new target text while preserving both the original text style and background texture. Existing methods suffer…
GAOT: Generating Articulated Objects Through Text-Guided Diffusion Models
Hao Sun, Lei Fan, Donglin Di +1
Articulated object generation has seen increasing advancements, yet existing models often lack the ability to be conditioned on text prompts. To address the significant gap between…
ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categories
Hai Ling, Jia Guo, Zhulin Tao +6
Anomaly detection (AD) aims to identify defects using normal-only training data. Existing anomaly detection benchmarks (e.g., MVTec-AD with 15 categories) cover only a narrow range…
Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detection
Jia Guo, Shuai Lu, Lei Fan +9
Unsupervised anomaly detection (UAD) has evolved from specialized single-class models to unified multi-class models, yet existing multi-class models significantly underperform the…
MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention
Qi Xie, Yongjia Ma, Donglin Di +2
Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained…
MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
Haoyu Wang, Hao Tang, Donglin Di +5
Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, lon…
PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
Chunji Lv, Zequn Chen, Donglin Di +5
Despite advances in physics-based 3D motion synthesis, current methods face key limitations: reliance on pre-reconstructed 3D Gaussian Splatting (3DGS) built from dense multi-view…
DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation
He Feng, Yongjia Ma, Donglin Di +3
Portrait animation aims to synthesize talking videos from a static reference face, conditioned on audio and style frame cues (e.g., emotion and head poses), while ensuring precise…