影响力指数

46.85/100

前 10%

全站排名 #6,412

发表论文14 篇

平均评分5.1

年均产出7.0 篇/年

Xi Li

Full Professor@Zhejiang University·中国·OpenReview

研究方向

image generation · AIGC · Neural Architecture Search · Cross-domain learning · Image segmentation · Object detection · object tracking

6.0

OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds

ICLR 2026Poster

通讯

5.5

All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning

ICLR 2026Poster

通讯

5.0

Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language Model

ICLR 2026Rejected

通讯

4.5

MultiCrafter: High-Fidelity Multi-Subject Generation via Spatially Disentangled Attention and Identity-Aware Reinforcement Learning

ICLR 2026Withdrawn

通讯

4.5

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning

ICLR 2026Withdrawn

通讯

4.5

Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation

ICLR 2026Rejected

通讯

6.4

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

ICLR 2025Poster

通讯

5.5

SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual Representation

ICLR 2025Rejected

通讯

5.5

CamI2V: Camera-Controlled Image-to-Video Diffusion Model

ICLR 2025Rejected

通讯

5.5

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning

ICLR 2025Rejected

通讯

4.8

PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals

合作者 (20)

Xi Li

OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds

All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning

Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language Model

MultiCrafter: High-Fidelity Multi-Subject Generation via Spatially Disentangled Attention and Identity-Aware Reinforcement Learning

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning

Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual Representation

CamI2V: Camera-Controlled Image-to-Video Diffusion Model

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning

CWPS: Efficient Channel-Wise Parameter Sharing for Knowledge Transfer

Towards Multi-Domain Chinese Document VQA: a New Dataset and Baseline Method

Hierarchical divide-and-conquer grouping for Zero shot learning

PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals