This collection holds the resources for the paper START: Spatial and Textual learning for chART understanding.
Zhuoming Liu
zhuomingliu
AI & ML interests
My research lies in Computer Vision and Machine Learning. I am particularly interested in Vision-Languauage Learning, Video Understanding.
Recent Activity
upvoted a paper about 1 hour ago
3DCodeVerse: Exploring 3D Worlds as Code authored a paper about 5 hours ago
Memory as Weights: Internalizing Long-Term History for Streaming Videos upvoted a paper about 11 hours ago
Memory as Weights: Internalizing Long-Term History for Streaming VideosOrganizations
None yet
models 8
zhuomingliu/MaLoW-Qwen3.5-0.8B
0.1B • Updated
zhuomingliu/MaLoW-Qwen3.5-2B
0.2B • Updated
zhuomingliu/MaLoW-Qwen3-VL-4B-Last8s
0.2B • Updated
zhuomingliu/MaLoW-Qwen3.5-4B-Last4s
0.2B • Updated
zhuomingliu/MaLoW-Qwen3.5-4B
0.2B • Updated
zhuomingliu/MaLoW-Qwen3.5-9B
0.3B • Updated
zhuomingliu/START
8B • Updated • 26
zhuomingliu/PAVE
Updated
datasets 9
zhuomingliu/MaLoW_others
Viewer • Updated • 10 • 102
zhuomingliu/testDataset
Preview • Updated • 1.55k
zhuomingliu/START_eval
Preview • Updated • 32
zhuomingliu/START_DATASET_RAW
Updated • 18
zhuomingliu/START-Dataset
Updated • 75
zhuomingliu/CS-Bench
Viewer • Updated • 692 • 27
zhuomingliu/PAVE_others
Updated • 223
zhuomingliu/PAVEDataset
Preview • Updated • 226
zhuomingliu/et_bench_test
Viewer • Updated • 200 • 17