Weixian Lei
6 papers · 2022–2025 · 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 · Gold
🗺️
Taxonomy Completionist
(12)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI · Artificial Intelligence
(5)
Computer Vision
(2)
Deep Learning
(2)
Natural Language Processing
(2)
Applications
(2)
Domain-Specific
(2)
Processing
(2)
Machine Learning
(1)
Robotics
(1)
Architectures
(1)
Capabilities
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Learning Paradigms
(1)
Keywords
multimodal learning
(3)
video question answering
(2)
vision transformer
(1)
question answering
(1)
egocentric vision
(1)
video retrieval
(1)
visual grounding
(1)
visual representation
(1)
modality alignment
(1)
human-robot interaction
(1)
vision-language model
(1)
multimodal large language model
(1)
zero-shot classification
(1)
instructional video
(1)
agent system
(1)
human-robot collaboration
(1)
gaze estimation
(1)
graphical user interface
(1)
affordance understanding
(1)
moment localization
(1)
Papers
Grounding Multimodal Large Language Model in GUI World
ICLR 2025
The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer
ICCV 2025
ViT-Lens: Towards Omni-modal Representations
CVPR 2024
GazeVQA: A Video Question Answering Dataset for Multiview Eye-Gaze Task-Oriented Collaborations
EMNLP 2023
AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant
EMNLP 2022
"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval"
ECCV 2022