Weijia Li's picture

1 12 3

Weijia Li

liweijia

·

https://liweijia.github.io/

liweijia

AI & ML interests

None yet

Recent Activity

upvoted a paper 9 days ago

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

upvoted a paper 22 days ago

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

upvoted a paper 2 months ago

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

View all activity

Organizations

None yet

authored 2 papers 4 months ago

GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation

Paper • 2504.02782 • Published Apr 3 • 58

LEGION: Learning to Ground and Explain for Synthetic Image Detection

Paper • 2503.15264 • Published Mar 19 • 21

authored a paper 10 months ago

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

Paper • 2410.09732 • Published Oct 13, 2024 • 56

authored 4 papers 11 months ago

Parrot Captions Teach CLIP to Spot Text

Paper • 2312.14232 • Published Dec 21, 2023 • 12

VIGC: Visual Instruction Generation and Correction

Paper • 2308.12714 • Published Aug 24, 2023 • 1

UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios

Paper • 2408.17267 • Published Aug 30, 2024 • 24

CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis

Paper • 2408.14765 • Published Aug 27, 2024 • 15