activity
20242026
collaborators

11 papers

cs.CV2026

Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation

Yu Cheng, Siyue Yao, Zhongang Qi +3

Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significa…

cs.CV2025

UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning

Ye Liu, Zongyang Ma, Junfu Pu +4

Recent advances in Large Multi-modal Models (LMMs) have demonstrated their remarkable success as general-purpose multi-modal assistants, with particular focuses on holistic image-…

cs.CV2025

DOGR: Towards Versatile Visual Document Grounding and Referring

Yinan Zhou, Yuxin Chen, Haokun Lin +6

With recent advances in Multimodal Large Language Models (MLLMs), grounding and referring capabilities have gained increasing attention for achieving detailed understanding and fle…

cs.CV2025

Taming Rectified Flow for Inversion and Editing

Jiangshan Wang, Junfu Pu, Zhongang Qi +6

Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation. Despite their robust genera…

cs.CV2025

DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation

Haoyu Zhao, Zhongang Qi, Cong Wang +5

With diffusion transformer (DiT) excelling in video generation, its use in specific tasks has drawn increasing attention. However, adapting DiT for pose-guided human image animatio…

cs.CV2025

Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion

Songsong Yu, Yuxin Chen, Zhongang Qi +5

With the rapid proliferation of 3D devices and the shortage of 3D content, stereo conversion is attracting increasing attention. Recent works introduce pretrained Diffusion Models…