6 15 22

Xingyu Fu

Fiaa

AI & ML interests

NLP, multimodal

Recent Activity

upvoted a paper about 1 month ago

Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

authored a paper 3 months ago

Science-T2I: Addressing Scientific Illusions in Image Synthesis

authored a paper 3 months ago

Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs

View all activity

Organizations

liked a dataset 5 months ago

nvidia/Nemotron-Post-Training-Dataset-v1

Viewer • Updated Aug 25, 2025 • 25.7M • 9.59k • 183

liked a model 7 months ago

meta-llama/Llama-3.1-8B

Text Generation • 8B • Updated Oct 16, 2024 • 1.49M • • 2.19k

liked 2 datasets 7 months ago

mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M

Viewer • Updated Nov 24, 2025 • 91.5M • 161k • 71

HuggingFaceM4/FineVision

Viewer • Updated Oct 21, 2025 • 24.2M • 109k • 484

liked a model 7 months ago

Qwen/Qwen3-8B

Text Generation • 8B • Updated Jul 26, 2025 • 11.7M • • 1.09k

liked a dataset 7 months ago

OpenGVLab/AS-100M

Viewer • Updated Mar 21, 2024 • 253 • 702 • 16

liked a dataset 8 months ago

m-a-p/PIN-200M

Viewer • Updated 29 days ago • 68.1k • 190k • 24

liked 2 datasets 10 months ago

HuggingFaceFV/finevideo

Viewer • Updated 14 days ago • 39.5k • 14.1k • 362

ReFocus/ReFocus_Data

Viewer • Updated Jul 10, 2025 • 17.2k • 418 • 1

liked a model over 1 year ago

ReFocus/Trained_Model

Image-Text-to-Text • Updated Feb 12, 2025 • 1

liked a dataset over 1 year ago

deepcs233/Visual-CoT

Preview • Updated Mar 11, 2025 • 3.29k • 62

liked a model over 1 year ago

stabilityai/stable-video-diffusion-img2vid-xt

Image-to-Video • Updated Jul 10, 2024 • 311k • 3.29k

liked a dataset over 1 year ago

HuggingFaceM4/the_cauldron

Viewer • Updated May 6, 2024 • 1.88M • 418k • 530

liked a Space over 1 year ago

VBench Leaderboard

📊

352

Submit video model evaluation results to a public benchmark

liked 3 datasets almost 2 years ago

liked a Space almost 2 years ago

Vision Arena (Testing VLMs side-by-side)

🖼

561

Explore AI-powered visual tasks in Vision Arena

liked a dataset almost 2 years ago

MUIRBENCH/MUIRBENCH

Viewer • Updated Jul 1, 2024 • 2.6k • 2.85k • 17

liked a dataset about 2 years ago

BLINK-Benchmark/BLINK

Viewer • Updated Sep 3, 2025 • 3.81k • 19.3k • 43