Xuan He PRO

hexuan21's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 datasets about 13 hours ago

TIGER-Lab/VideoFeedback2

Preview • Updated about 13 hours ago • 281

hexuan21/VideoScore2_video_cache

Viewer • Updated about 13 hours ago • 50k • 4

updated 2 models about 19 hours ago

videoscore2/vs2_qwen3vl_sft_27k_5e-5_2fps_960_720_8192

Image-to-Text • 770k • Updated about 19 hours ago • 84

videoscore2/vs2_internvl3_5_sft_27k_5e-5_2fps_960_720_8192

Any-to-Any • 695k • Updated about 19 hours ago • 77

published 2 models about 20 hours ago

videoscore2/vs2_qwen3vl_sft_27k_5e-5_2fps_960_720_8192

Image-to-Text • 770k • Updated about 19 hours ago • 84

videoscore2/vs2_internvl3_5_sft_27k_5e-5_2fps_960_720_8192

Any-to-Any • 695k • Updated about 19 hours ago • 77

upvoted a paper 4 days ago

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published 7 days ago • 57

updated a dataset about 1 month ago

hexuan21/anlp-hw2-outputs

Updated Nov 3 • 22

published a dataset about 1 month ago

hexuan21/anlp-hw2-outputs

Updated Nov 3 • 22

updated 2 datasets about 1 month ago

hexuan21/VideoScore_legacy

Preview • Updated Oct 27 • 136

hexuan21/VideoScore_legacy

Preview • Updated Oct 27 • 136

published a dataset about 1 month ago

hexuan21/weak-to-strong

Viewer • Updated Oct 23, 2024 • 1.21k • 85

liked a model about 2 months ago

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated Nov 4 • 5.45M • 2.94k

updated a Space about 2 months ago

Running on Zero

4

VideoScore2

📈

4

A thinking Video Evaluation Model

liked a Space about 2 months ago

Running on Zero

4

VideoScore2

📈

4

A thinking Video Evaluation Model

updated a model about 2 months ago

hexuan21/cs546_hw1_senti_cls

Text Classification • 22.7M • Updated Oct 17 • 4

published a model about 2 months ago

hexuan21/cs546_hw1_senti_cls

Text Classification • 22.7M • Updated Oct 17 • 4

upvoted a paper about 2 months ago

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

Paper • 2510.10666 • Published Oct 12 • 27

liked a model about 2 months ago

Qwen/Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated Oct 15 • 2.17M • • 523

updated a dataset about 2 months ago

TIGER-Lab/VideoFeedback2

Preview • Updated about 13 hours ago • 281