De Wen Soh
13 papers · 2014–2026 · 8 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 ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (35) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze π Academic Marathon Β· Half
π
Keyword Champion
(2)
π
Trend Setter
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(71)
Top co-authors
Research topics
Machine Learning
(12)
Core Methods
(7)
Artificial Intelligence
(6)
Computer Vision
(5)
Core AI
(5)
Deep Learning
(4)
Analysis
(4)
Learning Types
(4)
Optimization & Theory
(4)
Natural Language Processing
(3)
Application Areas
(3)
Models
(3)
Processing
(3)
Mathematics & Optimization
(2)
Bayesian & Probabilistic
(2)
Keywords
semantic segmentation
(2)
depth estimation
(2)
contrastive learning
(2)
conditional independence
(2)
3d reconstruction
(2)
data augmentation
(2)
gaussian graphical model
(2)
large language model
(2)
markov property
(2)
action recognition
(1)
named entity recognition
(1)
few-shot learning
(1)
text generation
(1)
information retrieval
(1)
self-supervised learning
(1)
document retrieval
(1)
graph theory
(1)
gaussian splatting
(1)
ensemble learning
(1)
sample complexity
(1)
Papers
VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation
CVPR 2026
CPCF: A Cross-Prompt Contrastive Framework for Referring Multimodal Large Language Models
ICML 2025
GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians
ICLR 2025
MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm
ICCV 2025
Performing Defocus Deblurring by Modeling its Formation Process
ICCV 2025
POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation
CVPR 2025
Re3Syn: A Dependency-Based Data Synthesis Framework for Long-Context Post-training
ACL 2025
Visual Prompting for One-shot Controllable Video Editing without Inversion
CVPR 2025
Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning
NAACL 2024
Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition
ACL 2024
Towards Better Characterization of Paraphrases
ACL 2022
Learning Unfaithful K-separable Gaussian Graphical Models
JMLR 2019
Testing Unfaithful Gaussian Graphical Models
NeurIPS 2014