Alert button
Picture for Yadong Mu

Yadong Mu

Alert button

InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior

Feb 07, 2024
Chenguo Lin, Yadong Mu

Viaarxiv icon

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

Feb 06, 2024
Yang Jin, Zhicheng Sun, Kun Xu, Kun Xu, Liwei Chen, Hao Jiang, Quzhe Huang, Chengru Song, Yuliang Liu, Di Zhang, Yang Song, Kun Gai, Yadong Mu

Viaarxiv icon

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

Sep 29, 2023
Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Chao Liao, Jianchao Tan, Quzhe Huang, Bin Chen, Chenyi Lei, An Liu, Chengru Song, Xiaoqiang Lei, Di Zhang, Wenwu Ou, Kun Gai, Yadong Mu

Figure 1 for Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Figure 2 for Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Figure 3 for Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Figure 4 for Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Viaarxiv icon

Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion

Sep 14, 2023
Peiran Xu, Yadong Mu

Figure 1 for Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion
Figure 2 for Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion
Figure 3 for Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion
Figure 4 for Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion
Viaarxiv icon

Unified Language-Vision Pretraining with Dynamic Discrete Visual Tokenization

Sep 09, 2023
Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Chao Liao, Jianchao Tan, Bin Chen, Chenyi Lei, An Liu, Chengru Song, Xiaoqiang Lei, Yadong Mu, Di Zhang, Wenwu Ou, Kun Gai

Figure 1 for Unified Language-Vision Pretraining with Dynamic Discrete Visual Tokenization
Figure 2 for Unified Language-Vision Pretraining with Dynamic Discrete Visual Tokenization
Figure 3 for Unified Language-Vision Pretraining with Dynamic Discrete Visual Tokenization
Figure 4 for Unified Language-Vision Pretraining with Dynamic Discrete Visual Tokenization
Viaarxiv icon

Regularizing Second-Order Influences for Continual Learning

Apr 20, 2023
Zhicheng Sun, Yadong Mu, Gang Hua

Figure 1 for Regularizing Second-Order Influences for Continual Learning
Figure 2 for Regularizing Second-Order Influences for Continual Learning
Figure 3 for Regularizing Second-Order Influences for Continual Learning
Figure 4 for Regularizing Second-Order Influences for Continual Learning
Viaarxiv icon

Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce

Apr 06, 2023
Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

Figure 1 for Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce
Figure 2 for Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce
Figure 3 for Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce
Figure 4 for Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce
Viaarxiv icon

Image Completion with Heterogeneously Filtered Spectral Hints

Nov 07, 2022
Xingqian Xu, Shant Navasardyan, Vahram Tadevosyan, Andranik Sargsyan, Yadong Mu, Humphrey Shi

Figure 1 for Image Completion with Heterogeneously Filtered Spectral Hints
Figure 2 for Image Completion with Heterogeneously Filtered Spectral Hints
Figure 3 for Image Completion with Heterogeneously Filtered Spectral Hints
Figure 4 for Image Completion with Heterogeneously Filtered Spectral Hints
Viaarxiv icon

Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

Sep 27, 2022
Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

Figure 1 for Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding
Figure 2 for Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding
Figure 3 for Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding
Figure 4 for Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding
Viaarxiv icon