Qianshan Wei
5 papers · 2024–2026 · 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
(15)
📈
Trend Setter
Venues
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI
(5)
Deep Learning
(4)
Models
(3)
Machine Learning
(2)
Robotics
(2)
Application Areas
(2)
Capabilities
(2)
Computer Vision
(1)
Natural Language Processing
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Resources & Methods
(1)
Keywords
machine unlearning
(2)
multimodal large language model
(2)
motion generation
(2)
concept unlearning
(2)
generative model
(1)
diffusion model
(1)
vision-language model
(1)
right to be forgotten
(1)
knowledge removal
(1)
multimodal language model
(1)
privacy-preserving model
(1)
concept forgetting
(1)
model utility preservation
(1)
adversarial attack defense
(1)
membership inference
(1)
gradient ascent
(1)
utility preservation
(1)
multimodal generative model
(1)
conceptual knowledge
(1)
human motion generation
(1)
Papers
Forget What Has Seen: Selective Concept Unlearning in Segmentation Foundation Models
AAAI 2026
Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models
ACL 2025
MotionCtrl: A Real-time Controllable Vision-Language-Motion Model
ICCV 2025
Scaling Large Motion Models with Million-Level Human Motions
ICML 2025
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
NeurIPS 2024