PaperHub
影响力指数
82.38/100
前 1.2%
全站排名 #750
发表论文22 篇
平均评分5.7
年均产出7.3 篇/年

Yao Zhao

Full Professor@Beijing Jiaotong University·中国·OpenReview
研究方向

computer vision · multimedia information processing · cross-media · watermarking · forensics · image compression · video processing

5.5
13

Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images

ICLR 2026Poster
5.0
20

DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning

ICLR 2026Rejected
通讯
5.0
27

PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion

ICLR 2026Rejected
4.8
16

On the Convergence Direction of Gradient Descent

ICLR 2026Poster
通讯
4.5
5

LRPO: Enhancing Blind Face Restoration through Online Reinforcement Learning

ICLR 2026Withdrawn
4.0
21

CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer

ICLR 2026Poster
通讯
4.0
8

From Editor to Dense Geometry Estimator

ICLR 2026Withdrawn
通讯
3.5
5

Adaptive Sensor Selection for Power Efficient 3D Object Detection on Autonomous Driving

ICLR 2026Withdrawn
三作
7.5
29

Towards Pre-trained Graph Condensation via Optimal Transport

NeurIPS 2025Poster
7.3
24

PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling

NeurIPS 2025Poster
三作
7.3
23

Learning from Disjoint Views: A Contrastive Prototype Matching Network for Fully Incomplete Multi-View Clustering

NeurIPS 2025Poster
通讯
6.8
26

Unifying Reconstruction and Density Estimation via Invertible Contraction Mapping in One-Class Classification

NeurIPS 2025Poster
6.8
26

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation

NeurIPS 2025Poster
通讯
6.8
22

Collapsed Language Models Promote Fairness

ICLR 2025Poster
6.5
26

IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation

ICLR 2025Rejected
通讯
6.4
24

DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing

NeurIPS 2025Poster
通讯
6.3
21

ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance

ICLR 2025Poster
5.6
35

Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation

ICLR 2025Poster
5.5
19

FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction

NeurIPS 2025Poster
合作者 (20)