Yang

Kaichengalex's activity

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

upvoted a paper 1 day ago

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs

Paper • 2510.13795 • Published 24 days ago • 55

updated a collection 2 days ago

SFT Dataset

Collection

5 items • Updated 2 days ago

liked a dataset 2 days ago

Open-Bee/Honey-Data-15M

Viewer • Updated 4 days ago • 14.8M • 58.2k • 71

upvoted an article 2 days ago

view article

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

By and 4 others •

4 days ago

• 34

upvoted an article 3 days ago

view article

Article

What makes good reasoning data

By •

10 days ago

• 29

upvoted a paper 5 days ago

Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum

Paper • 2510.27571 • Published 8 days ago • 16

updated a collection 5 days ago

MLLM4Embedding

Collection

7 items • Updated 5 days ago

upvoted a paper 5 days ago

UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings

Paper • 2511.00405 • Published 8 days ago • 5

upvoted a paper 6 days ago

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published 9 days ago • 102

updated a collection 9 days ago

SFT Dataset

Collection

5 items • Updated 2 days ago

upvoted a paper 11 days ago

Tongyi DeepResearch Technical Report

Paper • 2510.24701 • Published 11 days ago • 90

authored a paper 15 days ago

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

Paper • 2510.18795 • Published 18 days ago • 10

upvoted a paper 18 days ago

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

Paper • 2510.18795 • Published 18 days ago • 10

commented a paper 18 days ago

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

Paper • 2510.18795 • Published 18 days ago • 10 •

2

liked a dataset 18 days ago

OpenGVLab/AS-V2

Updated Mar 21, 2024 • 578 • 20

upvoted 2 papers 19 days ago

FineVision: Open Data Is All You Need

Paper • 2510.17269 • Published 20 days ago • 62

RL makes MLLMs see better than SFT

Paper • 2510.16333 • Published 22 days ago • 47

updated a collection 22 days ago

MLLM4Embedding

Collection

7 items • Updated 5 days ago

authored a paper 23 days ago

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

Paper • 2509.23661 • Published Sep 28 • 44