Bellevue, WA

Xiang Li

Advanced
@lxa9867

xAI | ex-Google Deepmind, CMU | Multimodal Understanding & Generation

lxa9867.github.io/

Awesome-Autoregressive-Visual-Generation. This is a repo to track the latest autoregressive visual generation papers.

431

ImageFolder. High-performance Image Tokenizers for VAR and AR

307

ControlVAR. This is the official implementation for ControlVAR.

129

R2VOS. Robust Referring Video Object Segmentation with Cyclic Structural Consistency [ICCV 2023]

31

PaintSeg. [NeurIPS 2023] Official Implementation of "PaintSeg: Painting Pixels for Training-free Segmentation"

14

QSD. [CVPR 2024] "Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition"

12

r2bench. [ECCV 2024] R2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations

11

VAF. [ACM MM 2023] Rethinking Voice-Face Correlation: A Geometry View

8

StyleT2I-main. Python

1
9
Apply