collaborators

5 papers

cs.CV2026

Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?

Muquan Li, Yingyi Ma, Yihong Huang +5

Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness u…

cs.CV2026

One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems

Yufei Shi, Weilong Yan, Naixuan Huang +5

Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail to satisfy three key requirements…

cs.CV2026

Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space

Xiaoce Wang, Sifan Zhou, Kaifei Wang +4

Recent advances in diffusion transformers (DiTs) have enabled promising single-turn image editing capabilities. However, multi-turn editing often leads to progressive semantic drif…

cs.CV2026

Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching

Xin Hu, Ke Qin, Wen Yin +3

Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as…

cs.CV2025

SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning

Xin Hu, Ke Qin, Guiduo Duan +3

Panoptic Scene Graph Generation (PSG) integrates instance segmentation with relation understanding to capture pixel-level structural relationships in complex scenes. Although recen…