3 citations · 4 across the 10 of their papers we have counts for
7 papers · 1 filter
ChatUMM: Robust Context Tracking for Conversational Interleaved Generation
Wenxun Dai, Zhiyuan Zhao, Yule Zhong +12
Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functioning as solvers for independent…
WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens
Jian Yang, Dacheng Yin, Xiaoxuan He +6
Recent progress in multimodal large language models (MLLMs) has highlighted the challenge of efficiently bridging pre-trained Vision-Language Models (VLMs) with Diffusion Models. W…
Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
Jiaqi Huang, Zunnan Xu, Ting Liu +4
In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particula…
LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
Jiahao Wang, Ning Kang, Lewei Yao +12
In this paper, we investigate how to convert a pre-trained Diffusion Transformer (DiT) into a linear DiT, as its simplicity, parallelism, and efficiency for image generation. Throu…
ColorFlow: Retrieval-Augmented Image Sequence Colorization
Junhao Zhuang, Xuan Ju, Zhaoyang Zhang +4
Automatic black-and-white image sequence colorization while preserving character and object identity (ID) is a complex task with significant market demand, such as in cartoon or co…
RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting
Zhexi Peng, Tianjia Shao, Yong Liu +4
We present Real-time Gaussian SLAM (RTG-SLAM), a real-time 3D reconstruction system with an RGBD camera for large-scale environments using Gaussian splatting. The system features a…
DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos
Xiuzhe Wu, Xiaoyang Lyu, Qihao Huang +4
Although considerable advancements have been attained in self-supervised depth estimation from monocular videos, most existing methods often treat all objects in a video as static…