Pingyu Wu
8 papers · 2022–2026 · 5 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 · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(17)
Top co-authors
Research topics
Artificial Intelligence
(3)
Computer Vision
(3)
Deep Learning
(3)
Architectures
(3)
Core AI
(3)
Generation · Computer Vision
(3)
Machine Learning
(2)
Learning Types
(2)
Models
(2)
Computer Science
(1)
Natural Language Processing
(1)
Analysis
(1)
Applications
(1)
Core Methods
(1)
Generation · Natural Language Processing
(1)
Keywords
variational autoencoder
(2)
semantic parsing
(1)
synthetic data generation
(1)
image captioning
(1)
conditional generation
(1)
gaussian splatting
(1)
multimodal learning
(1)
structured output
(1)
neural representation
(1)
generative model
(1)
diffusion model
(1)
question answering
(1)
vision-language model
(1)
video reconstruction
(1)
concept extraction
(1)
latent diffusion
(1)
retrieval-augmented generation
(1)
role-playing agent
(1)
3d gaussian
(1)
video generation
(1)
Papers
MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement
AAAI 2026
Trait Activation in Silicon: A Situation-Aware Framework for Psychologically Grounded Role-Playing
ACL 2026
BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs
CVPR 2025
Improved Video VAE for Latent Video Diffusion Model
CVPR 2025
MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
NAACL 2025
SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets
ICCV 2025
Spatial-Aware Token for Weakly Supervised Object Localization
ICCV 2023
Background Activation Suppression for Weakly Supervised Object Localization
CVPR 2022