Junfeng Luo
9 papers · 2021–2026 · 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 ↓
π
Conference Polyglot Β· Silver
π
Academic Marathon Β· Sprint
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(34)
ποΈ
Keyword Collector
(54)
Top co-authors
Research topics
Keywords
document understanding
(3)
multimodal large language model
(3)
visual question answering
(2)
network architecture
(1)
attention mechanism
(1)
multimodal learning
(1)
preference learning
(1)
autonomous vehicle
(1)
autonomous driving
(1)
text-to-image generation
(1)
instruction tuning
(1)
diffusion model
(1)
deep neural network
(1)
reward model
(1)
vision-language model
(1)
feature fusion
(1)
lane detection
(1)
supervised fine-tuning
(1)
image generation
(1)
semantic segmentation
(1)
Papers
PositionIC: Unified Position and Identity Consistency for Image Customization
CVPR 2026
PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback
CVPR 2026
PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
CVPR 2026
A Token-level Text Image Foundation Model for Document Understanding
ICCV 2025
InstructOCR: Instruction Boosting Scene Text Spotting
AAAI 2025
Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
CVPR 2025
Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review
ACL 2025
Rethinking BiSeNet for Real-Time Semantic Segmentation
CVPR 2021
Structure Guided Lane Detection
IJCAI 2021