2 10 12

Zijie Xin

xxayt

https://xxayt.github.io/

xxayt

AI & ML interests

multi-modal learning, AIGC

Recent Activity

upvoted a paper about 3 hours ago

Stage-adaptive Token Selection for Efficient Omni-modal LLMs

authored a paper about 1 month ago

Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data

upvoted a paper about 2 months ago

MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos

View all activity

Organizations

liked a dataset 9 months ago

NVEagle/VideoITG-40K

Preview • Updated Aug 8, 2025 • 109 • 3

liked a model 9 months ago

OpenGVLab/InternVL_2_5_HiCo_R16

Video-Text-to-Text • 8B • Updated Feb 13, 2025 • 238 • 6

liked a dataset about 1 year ago

TheEighthDay/SeekWorld

Preview • Updated Apr 20, 2025 • 35 • 6

liked a Space about 1 year ago

Open VLM Video Leaderboard

🌎

135

VLMEvalKit Eval Results in video understanding benchmark

liked a dataset about 1 year ago

xxayt/MGSV-EC

Viewer • Updated Aug 5, 2025 • 53.2k • 46 • 2

liked 3 models over 1 year ago

liked a dataset over 1 year ago

AIMClab-RUC/ChinaOpen

Viewer • Updated Nov 15, 2023 • 1.09k • 62 • 3

liked 2 models over 2 years ago

m-a-p/MERT-v1-330M

Audio Classification • Updated May 25, 2025 • 48k • 86

openai/clip-vit-base-patch32

Zero-Shot Image Classification • Updated Feb 29, 2024 • 21.7M • 937

liked a Space almost 3 years ago

BLIP2

🌖

586

Generate captions and chat responses from your images