Junyuan Zhang
8 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 · Bronze
🗺️
Taxonomy Completionist
(18)
👥
Mega-Team · Legion
❓
The Questioner
Venues
Top co-authors
Research topics
Artificial Intelligence
(6)
Machine Learning
(4)
Core AI
(4)
Deep Learning
(3)
Application Areas
(3)
Learning Paradigms
(3)
Natural Language Processing
(2)
Applications
(2)
Models
(2)
Optimization & Theory · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Computer Vision
(1)
Domain-Specific
(1)
Keywords
vision-language model
(3)
model aggregation
(2)
data heterogeneity
(2)
federated learning
(2)
multimodal learning
(1)
document understanding
(1)
document parsing
(1)
autonomous driving
(1)
efficient inference
(1)
knowledge base
(1)
computational efficiency
(1)
synthetic data
(1)
client sampling
(1)
multimodal large language model
(1)
coarse-to-fine strategy
(1)
token pruning
(1)
retrieval-augmented generation
(1)
inference acceleration
(1)
multimodal input
(1)
inference latency
(1)
Papers
JARVIS or Ultron? A Survey on the Safety and Security Threats of Computer-Using Agents
ACL 2026
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
ACL 2026
Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
CVPR 2026
TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
CVPR 2026
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
ICCV 2025
Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More
EMNLP 2025
FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning
CVPR 2024
One-shot Federated Learning via Synthetic Distiller-Distillate Communication
NeurIPS 2024