Xinyu Huang's picture

Xinyu Huang

xinyu1205

·

xinyu1205

AI & ML interests

Multi-Modal Learning, Multi-Label Learning

Recent Activity

liked a model 30 days ago

deepseek-ai/DeepSeek-V4-Pro

liked a Space about 1 month ago

limuloo1999/RefineAnything

upvoted a paper 8 months ago

Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

View all activity

Organizations

Papers 4

arxiv:2507.05920

arxiv:2310.15200

arxiv:2306.03514

arxiv:2303.05657

spaces 1

Recognize Detect Segment Anything

models 3

xinyu1205/recognize_anything_model

Image-to-Text • Updated Oct 25, 2023 • 51

xinyu1205/recognize-anything-plus-model

Zero-Shot Image Classification • Updated Oct 25, 2023 • 48

xinyu1205/tag2text_model

Updated Jun 14, 2023 • 2

datasets 5

xinyu1205/mme_realworld_train_21690

Viewer • Updated Apr 29, 2025 • 47.6k • 463

xinyu1205/mme_realworld_lite_1919_vstar_191_sum_2110

Viewer • Updated Apr 29, 2025 • 2.54k • 231

xinyu1205/recognize-anything-dataset

Viewer • Updated Nov 28, 2023 • 3.36M • 120 • 3

xinyu1205/recognize-anything-dataset-14m

Viewer • Updated Oct 23, 2023 • 3.5M • 30 • 3

xinyu1205/recognize-anything-plus-model-tag-descriptions

Preview • Updated Oct 23, 2023 • 34 • 3