影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
68.92/100
前 2.8%
全站排名 #1,831
发表论文21 篇
平均评分
年均产出7.0 篇/年
Zongxin Yang
研究方向
3D vision · Video segmentation · Visual object tracking · Video object segmentation · Multi-modal Learning · Computer vision · Vision generation
23
Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions
ICLR 2026Poster
二作14
TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracing
ICLR 2026Rejected
16
UUE: Untargeted Language Model Unlearning via Null-Space-Guided Editing with Lightweight Adapters
ICLR 2026Rejected
22
Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration
ICLR 2026Rejected
二作17
HMFusion: Hierarchical Multi-Modality Fusion for CAD Representation
ICLR 2026Rejected
二作31
Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
ICLR 2026Poster
三作25
BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
ICLR 2026Poster
三作5
Entropy-Guided Automated Progressive Pruning for Diffusion and Flow Models
ICLR 2026Withdrawn
6
Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation
ICLR 2026Rejected
二作24
X-Field: A Physically Informed Representation for 3D X-ray Reconstruction
NeurIPS 2025Spotlight
23
Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
NeurIPS 2025Poster
30
3DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance Generation
ICLR 2025Spotlight
三作26
Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration
NeurIPS 2025Rejected
二作15
Origin Identification for Text-Guided Image-to-Image Diffusion Models
ICML 2025Poster
三作31
Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
ICLR 2025Poster
二作30
3D Object Manipulation in a Single Image Using Generative Models
ICLR 2025Rejected
三作6
SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons
ICLR 2025Withdrawn
二作6
Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation
ICLR 2025Withdrawn
二作5
Generalizable Origin Identification for Text-Guided Image-to-Image Diffusion Models
ICLR 2025Withdrawn
三作