QU Tianyuan

TainU's activity

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

authored 3 papers 2 days ago

LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model

Paper • 2312.17240 • Published Dec 28, 2023 • 1

RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models

Paper • 2505.19125 • Published May 25, 2025

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models

Paper • 2512.16561 • Published Dec 18, 2025 • 20

authored a paper 3 days ago

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Paper • 2603.06569 • Published 5 days ago • 95

upvoted a paper 3 days ago

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Paper • 2603.06569 • Published 5 days ago • 95

liked a Space 3 days ago

Running on L40S

4

Penguin VL 8B

💬

4

a compact Vision-Language Model

upvoted a collection 3 days ago

AI Lab

Collection

4 items • Updated 1 day ago • 10

liked 3 models 3 days ago

tencent/Penguin-Encoder

Feature Extraction • 0.4B • Updated 3 days ago • 572 • 15

tencent/Penguin-VL-2B

Text Generation • 2B • Updated about 2 hours ago • 326 • 24

tencent/Penguin-VL-8B

Text Generation • 9B • Updated about 2 hours ago • 1.34k • 56

liked a dataset 2 months ago

WeiChow/CrispEdit-2M

Viewer • Updated Dec 29, 2025 • 2.29M • 7.03k • 15

liked a model 3 months ago

yuxinhk/N3D-VLM

8B • Updated Dec 17, 2025 • 189 • 3

updated a model 3 months ago

TainU/RePlan-Qwen2.5-VL-7B

Image-to-Image • 8B • Updated Dec 19, 2025 • 760 • 13

New activity in TainU/RePlan-Qwen2.5-VL-7B 3 months ago

Improve model card: Add metadata, fix paper link, and add GitHub badge

#1 opened 3 months ago by

nielsr

liked a model 3 months ago

TainU/RePlan-Qwen2.5-VL-7B

Image-to-Image • 8B • Updated Dec 19, 2025 • 760 • 13

liked a dataset 3 months ago

TainU/IV-Edit

Viewer • Updated Dec 19, 2025 • 1.96k • 255 • 4

New activity in TainU/IV-Edit 3 months ago

Improve dataset card: Add task categories, language, fix paper link, and add code link

#1 opened 3 months ago by

nielsr

upvoted a paper 3 months ago

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models

Paper • 2512.16561 • Published Dec 18, 2025 • 20

authored a paper 3 months ago

RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

Paper • 2512.16864 • Published Dec 18, 2025 • 11

upvoted a paper 3 months ago

RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

Paper • 2512.16864 • Published Dec 18, 2025 • 11