Xingkai Yu
4 papers · 2024–2026 · 2 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
(12)
Top co-authors
Research topics
Artificial Intelligence
(4)
Deep Learning
(4)
Architectures
(4)
Core AI · Artificial Intelligence
(4)
Computer Vision
(2)
Core AI · Computer Vision
(2)
Learning Types
(2)
Machine Learning
(1)
Natural Language Processing
(1)
Application Areas
(1)
Models
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
multimodal understanding
(2)
mixture of expert
(2)
vision-language model
(2)
image generation
(2)
autoregressive model
(2)
multimodal learning
(2)
rectified flow
(1)
expert specialization
(1)
knowledge sharing
(1)
multimodal generation
(1)
large language model
(1)
visual encoding
(1)
sparsity allocation
(1)
unified multimodal model
(1)
conditional memory
(1)
autoregressive framework
(1)
transformer architecture
(1)
deep sparse embedding
(1)
model architecture
(1)
scaling law
(1)
Papers
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
ACL 2026
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
CVPR 2025
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
CVPR 2025
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
ACL 2024