arxiv:2512.22799
Jingchao Wang
jcwang0602
AI & ML interests
MLLM, Visual Object Tracking, Visual Grounding
Recent Activity
updated a dataset 2 days ago
opendatalab/MolRecBench-Wild published a dataset 23 days ago
opendatalab/MolRecBench-Wild upvoted a paper 3 months ago
VPTracker: Global Vision-Language Tracking via Visual Prompt and MLLMOrganizations
models 6
jcwang0602/VPTracker
Image-Text-to-Text • 4B • Updated • 9 • 1
jcwang0602/MLLMSeg_InternVL2_5_8B_RES
Image Segmentation • 8B • Updated • 10 • 1
jcwang0602/MLLMSeg_InternVL2_5_1B_RES
Image Segmentation • 1.0B • Updated • 9
jcwang0602/MLLMSeg_InternVL2_5_2B_RES
Image Segmentation • 2B • Updated • 5
jcwang0602/MLLMSeg_InternVL2_5_4B_RES
Image Segmentation • 4B • Updated • 4
jcwang0602/MLLMSeg_InternVL2_5_8B_GRES
Image Segmentation • 8B • Updated • 6 • 2
datasets 0
None public yet