Yangguang Li
- Papers
- 16
Cite
Notes
Only stored in your browser.
Authored papers
16Flow-GRPO: Training Flow Matching Models via Online RL
arXiv 2025
Transition Models: Rethinking the Generative Learning Objective
arXiv 2025
ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
arXiv 2025
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
arXiv 2025
HoloPart: Generative 3D Part Amodal Segmentation
arXiv 2025
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
arXiv 2025
SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
ICCV 2025
MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
CVPR 2025 1
Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT
arXiv 2024
TEXGen: a Generative Diffusion Model for Mesh Textures
arXiv 2024
TripoSR: Fast 3D Object Reconstruction from a Single Image
arXiv 2024
EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion
CVPR 2024 1
SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM
arXiv 2023
A Mixture of Surprises for Unsupervised Reinforcement Learning
arXiv 2022
BEVBert: Multimodal Map Pre-training for Language-guided Navigation
ICCV 2023 1
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
supervision-exists-everywhere-a-data
Affiliations
Frequent co-authors
10from 16 papers