Fangyong Wang
6 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
⭐
Rising Star
(6)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Computer Vision
(4)
Deep Learning
(3)
Machine Learning
(3)
Analysis
(3)
Artificial Intelligence
(2)
Application Areas
(2)
Learning Types · Machine Learning
(2)
Architectures
(1)
Core AI
(1)
Domain-Specific
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Processing
(1)
Techniques
(1)
Keywords
attention mechanism
(2)
vision-language alignment
(2)
open-vocabulary semantic segmentation
(2)
point cloud
(2)
domain adaptation
(1)
knowledge transfer
(1)
knowledge distillation
(1)
cross-modal learning
(1)
3d vision
(1)
class-incremental learning
(1)
visual grounding
(1)
state space model
(1)
parameter-efficient tuning
(1)
dense prediction
(1)
lidar point cloud
(1)
prompt tuning
(1)
cosine similarity
(1)
distribution discrepancy
(1)
lidar semantic segmentation
(1)
3d semantic segmentation
(1)
Papers
BeyondSparse: Facilitating Mamba to Enhance Cross-Domain 3D Semantic Segmentation in Adverse Weather
AAAI 2026
Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation
CVPR 2026
PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation
AAAI 2026
Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
AAAI 2026
xMHashSeg: Cross-modal Hash Learning for Training-free Unsupervised LiDAR Semantic Segmentation
AAAI 2026
Task-Aware Prompt Gradient Projection for Parameter-Efficient Tuning Federated Class-Incremental Learning
ICCV 2025