Guanglu Song
- Papers
- 15
Cite
Notes
Only stored in your browser.
Authored papers
15Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
arXiv 2026
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
arXiv 2024
Phased Consistency Models
arXiv 2024
AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data
arXiv 2024
Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation
arXiv 2024
MoVA: Adapting Mixture of Vision Experts to Multimodal Context
arXiv 2024
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
arXiv 2024
FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis
arXiv 2024
Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance
CVPR 2024 1
Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising
arXiv 2023
Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction
ICCV 2023 1
DETRs with Collaborative Hybrid Assignments Training
ICCV 2023 1
UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning
arXiv 2022
Large-batch Optimization for Dense Visual Predictions
arXiv 2022
Self-slimmed Vision Transformer
arXiv 2021
Affiliations
Frequent co-authors
10from 15 papers