TianchengGu

TianchengGu's activity

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

liked a Space 1 day ago

Running on CPU Upgrade

941

941

The Smol Training Playbook: The Secrets to Building World-Class LLMs

📝

updated a collection 1 day ago

Datasets

Collection

8 items • Updated 1 day ago

updated a collection 12 days ago

Datasets

Collection

8 items • Updated 1 day ago

authored a paper 17 days ago

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning

Paper • 2510.13515 • Published 18 days ago • 11

updated a dataset 18 days ago

TianchengGu/UniME-V2-Training-Datasets

Viewer • Updated 18 days ago • 1.99M • 77 • 3

updated 4 models 18 days ago

TianchengGu/UniME-V2-reranker-Qwen25VL-7B

Image-Text-to-Text • 8B • Updated 18 days ago • 30 • 2

TianchengGu/UniME-V2-LLaVA-OneVision-8B

Image-Text-to-Text • 8B • Updated 18 days ago • 18 • 2

TianchengGu/UniME-V2-Qwen2VL-7B

Image-Text-to-Text • 8B • Updated 18 days ago • 25 • 2

TianchengGu/UniME-V2-Qwen2VL-2B

Image-Text-to-Text • 2B • Updated 18 days ago • 70 • 2

upvoted a paper 18 days ago

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning

Paper • 2510.13515 • Published 18 days ago • 11

published a dataset 18 days ago

TianchengGu/UniME-V2-Training-Datasets

Viewer • Updated 18 days ago • 1.99M • 77 • 3

published 4 models 18 days ago

TianchengGu/UniME-V2-Qwen2VL-2B

Image-Text-to-Text • 2B • Updated 18 days ago • 70 • 2

TianchengGu/UniME-V2-LLaVA-OneVision-8B

Image-Text-to-Text • 8B • Updated 18 days ago • 18 • 2

TianchengGu/UniME-V2-Qwen2VL-7B

Image-Text-to-Text • 8B • Updated 18 days ago • 25 • 2

TianchengGu/UniME-V2-reranker-Qwen25VL-7B

Image-Text-to-Text • 8B • Updated 18 days ago • 30 • 2

upvoted a paper 25 days ago

Multi-Agent Tool-Integrated Policy Optimization

Paper • 2510.04678 • Published 27 days ago • 30

upvoted a paper 29 days ago

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28 • 44

liked a Space about 1 month ago

Running

197

197

FineVision: Open Data is All You Need

📝

A new open-source dataset for training VLMs

upvoted a paper about 1 month ago

Video models are zero-shot learners and reasoners

Paper • 2509.20328 • Published Sep 24 • 96