Cong Wei
12 papers · 2023–2026 · 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (29) 👥 Mega-Team · Squad
🗃️
Keyword Collector
(73)
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI · Artificial Intelligence
(9)
Computer Vision
(8)
Deep Learning
(7)
Machine Learning
(5)
Natural Language Processing
(4)
Application Areas
(4)
Processing
(4)
Architectures
(3)
Learning Types · Deep Learning
(3)
Analysis
(2)
Core AI · Computer Vision
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Resources & Methods
(2)
Keywords
video understanding
(4)
visual language model
(2)
efficient computing
(2)
vision-language model
(2)
semantic segmentation
(2)
multimodal learning
(2)
multimodal large language model
(2)
visual large language model
(2)
video generation
(1)
object detection
(1)
benchmark evaluation
(1)
image editing
(1)
visual reasoning
(1)
visual grounding
(1)
chain-of-thought reasoning
(1)
multi-task learning
(1)
universal segmentation
(1)
data augmentation
(1)
importance sampling
(1)
instruction following
(1)
Papers
UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
CVPR 2026
Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models
CVPR 2026
Advancing Visual Large Language Model for Multi-granular Versatile Perception
ICCV 2025
HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver
CVPR 2025
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
ICCV 2025
OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision
ICLR 2025
Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers
ICCV 2025
VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation
CVPR 2025
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
CVPR 2024
UniIR: Training and Benchmarking Universal Multimodal Information Retrievers
ECCV 2024
VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
ACL 2024
Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers
CVPR 2023