Zili Wang's picture

4 9 4

Zili Wang

MarkWang

·

MarkXCloud

AI & ML interests

Multi-modality learning and inference acceleration

Recent Activity

upvoted a paper about 1 month ago

Taming Modality Entanglement in Continual Audio-Visual Segmentation

upvoted a paper about 2 months ago

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

upvoted a paper 3 months ago

R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

View all activity

Organizations

liked a model 4 months ago

YannQi/R-4B

Image-Text-to-Text • 5B • Updated Sep 4 • 51.4k • 172

liked 3 Spaces over 2 years ago

Detection Metrics

Compute object detection metrics using COCO style

Open Object Detection Leaderboard

Request evaluation for a new model

FastSAM

Segment images using texts, points, or everything mode