TainU/RePlan-Qwen2.5-VL-7B
Image-to-Image • 8B • Updated
• 571 • 13
QU Tianyuan
TainU
AI & ML interests
None yet
Recent Activity
authored
a paper
1 day ago
LISA++: An Improved Baseline for Reasoning Segmentation with Large
Language Model authored
a paper
1 day ago
RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large
Multi-modal Models authored
a paper
2 days ago
N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models Organizations
