6 56 49

Haiwen Diao

Paranioar

https://Paranioar.github.io/

AI & ML interests

Vision-and-Language, Parameter-efficient Transfer Learning, Multi-modal Large Language Model

Recent Activity

published a model about 4 hours ago

Paranioar/NEO1_5-2B-SFT

published a model about 4 hours ago

Paranioar/NEO1_5-9B-SFT

updated a model about 4 hours ago

Paranioar/NEO1_5-2B-SFT

View all activity

Organizations

liked a model 11 days ago

sensenova/SenseNova-U1-8B-MoT-Infographic

Any-to-Any • 18B • Updated 11 days ago • 5.29k • 39

liked 3 models 15 days ago

liked a model 24 days ago

sensenova/SenseNova-U1-8B-MoT-8step-preview

Any-to-Any • 18B • Updated 13 days ago • 445 • 12

liked 2 models 26 days ago

sensenova/SenseNova-U1-8B-MoT-SFT

Any-to-Any • 18B • Updated 13 days ago • 1.97k • 51

sensenova/SenseNova-U1-8B-MoT

Any-to-Any • 18B • Updated 12 days ago • 23.3k • 277

liked 2 models 5 months ago

Paranioar/NEO1_0-9B-SFT

Image-Text-to-Text • 10B • Updated Oct 21, 2025 • 34 • 6

Paranioar/NEO1_0-2B-SFT

Image-Text-to-Text • 3B • Updated Oct 21, 2025 • 96 • 10

liked a dataset 6 months ago

VLMEval/OpenVLMRecords

Updated Apr 8, 2025 • 1.14k • 15

liked a model 12 months ago

black-forest-labs/FLUX.1-Fill-dev

Updated Jun 27, 2025 • 267k • 1.04k

liked a model about 1 year ago

black-forest-labs/FLUX.1-schnell

Text-to-Image • Updated Aug 16, 2024 • 574k • • 4.94k

liked a model over 1 year ago

BAAI/EVE-7B-HD-v2.0

14B • Updated Feb 11, 2025 • 215 • 9

liked 2 datasets over 1 year ago

lmms-lab/LLaVA-Video-178K

Viewer • Updated Oct 11, 2024 • 1.63M • 28.7k • 195

MAmmoTH-VL/MAmmoTH-VL-Instruct-12M

Viewer • Updated Jan 5, 2025 • 37M • 3.63k • 64

liked 5 Spaces over 1 year ago

MM-Vet Evaluator

🐨

Evaluate AI model predictions with correctness scores

Qwen2-VL-7B

🔥

269

Answer questions about uploaded images

Florence Llama

💬

Generate text responses from images and text input

Llava Llama-3 8B

🔥

Meta Llama3 8b with Llava Multimodal capabilities

VBench Leaderboard

📊

354

Submit video model evaluation results to a public benchmark