10 13 4

Ye Liu

yeliudev

21world's profile picture

Gargaz's profile picture

Otolith's profile picture

https://yeliu.dev/

yeliudev
yeliudev

AI & ML interests

Vision & Language

Recent Activity

updated a dataset 4 days ago

yeliudev/datasets

upvoted a paper 5 days ago

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

updated a model 18 days ago

PolyU-ChenLab/UniPixel-7B

View all activity

Organizations

yeliudev 's collections 4

UniPixel

[NeurIPS 2025] UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning

Running on Zero

5

5

UniPixel

🔮

An MLLM for Unified Object Referring and Segmentation
PolyU-ChenLab/UniPixel-3B

Video-Text-to-Text • 4B • Updated Oct 4 • 1.39k • 3
PolyU-ChenLab/UniPixel-7B

Video-Text-to-Text • 8B • Updated 18 days ago • 80
PolyU-ChenLab/UniPixel-SFT-1M

Preview • Updated Oct 4 • 2.17k • 2

E.T. Bench

[NeurIPS 2024] E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

PolyU-ChenLab/ETBench

Viewer • Updated Oct 29, 2024 • 5 • 351 • 4
PolyU-ChenLab/ET-Instruct-164K

Viewer • Updated Sep 27, 2024 • 115k • 296 • 4
PolyU-ChenLab/ETChat-Phi3-Mini-Stage-1

Video-Text-to-Text • 5B • Updated Oct 29, 2024 • 1
PolyU-ChenLab/ETChat-Phi3-Mini-Stage-2

5B • Updated Sep 27, 2024

VideoMind

VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning

Running on Zero

36

36

VideoMind 2B

💡

A Chain-of-LoRA Agent for Long Video Reasoning
yeliudev/VideoMind-2B

Video-Text-to-Text • Updated Oct 4 • 36 • 2
yeliudev/VideoMind-7B

Video-Text-to-Text • Updated Oct 4 • 8 • 4
yeliudev/VideoMind-Dataset

Preview • Updated Oct 4 • 6.67k • 8

R2-Tuning

[ECCV 2024] R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Sleeping

6

6

R2-Tuning

🌀

[ECCV 2024] Localizing moments in videos via text queries
yeliudev/R2-Tuning

Updated Apr 17, 2024 • 1
R^2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Paper • 2404.00801 • Published Mar 31, 2024

UniPixel

[NeurIPS 2025] UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning

Running on Zero

5

5

UniPixel

🔮

An MLLM for Unified Object Referring and Segmentation
PolyU-ChenLab/UniPixel-3B

Video-Text-to-Text • 4B • Updated Oct 4 • 1.39k • 3
PolyU-ChenLab/UniPixel-7B

Video-Text-to-Text • 8B • Updated 18 days ago • 80
PolyU-ChenLab/UniPixel-SFT-1M

Preview • Updated Oct 4 • 2.17k • 2

VideoMind

VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning

Running on Zero

36

36

VideoMind 2B

💡

A Chain-of-LoRA Agent for Long Video Reasoning
yeliudev/VideoMind-2B

Video-Text-to-Text • Updated Oct 4 • 36 • 2
yeliudev/VideoMind-7B

Video-Text-to-Text • Updated Oct 4 • 8 • 4
yeliudev/VideoMind-Dataset

Preview • Updated Oct 4 • 6.67k • 8

E.T. Bench

[NeurIPS 2024] E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

PolyU-ChenLab/ETBench

Viewer • Updated Oct 29, 2024 • 5 • 351 • 4
PolyU-ChenLab/ET-Instruct-164K

Viewer • Updated Sep 27, 2024 • 115k • 296 • 4
PolyU-ChenLab/ETChat-Phi3-Mini-Stage-1

Video-Text-to-Text • 5B • Updated Oct 29, 2024 • 1
PolyU-ChenLab/ETChat-Phi3-Mini-Stage-2

5B • Updated Sep 27, 2024

R2-Tuning

[ECCV 2024] R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Sleeping

6

6

R2-Tuning

🌀

[ECCV 2024] Localizing moments in videos via text queries
yeliudev/R2-Tuning

Updated Apr 17, 2024 • 1
R^2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Paper • 2404.00801 • Published Mar 31, 2024

Ye Liu

AI & ML interests

Recent Activity

Organizations

yeliudev 's collections 4

UniPixel

VideoMind 2B

R2-Tuning

UniPixel

VideoMind 2B

R2-Tuning