Kaicheng Yang
Kaichengalex
·
AI & ML interests
Multimodal Representation Learning/ Vision-Language Pretraining/DeepResearch
Recent Activity
liked a model about 15 hours ago
lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct liked a Space 13 days ago
joelniklaus/harness-leaderboard updated a collection 14 days ago
VideoDatasetOrganizations
None yet
PreTraining
Fully-Open
GUI Dataset
UniME-R1
VideoDataset
DanQing
Large-scale Chinese Image-Text Datasets
RWKV-CLIP
Web-Person Dataset
Vision-Language Dataset
MLLM4Embedding
-
GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
Paper • 2412.16855 • Published • 5 -
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
Paper • 2410.05160 • Published • 4 -
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
Paper • 2507.04590 • Published • 17
Ego
Robotic
Multi-Image Dataset
OCR Dataset
Doc Data
CoT Dataset
-
opendatalab/ChartVerse-SFT-1.8M
Viewer • Updated • 1.88M • 4.98k • 141 -
OpenDataArena/MMFineReason-1.8M-Qwen3-VL-235B-Thinking
Viewer • Updated • 1.81M • 2.64k • 127 -
OpenDataArena/MMFineReason-SFT-123K-Qwen3-VL-235B-Thinking
Viewer • Updated • 123k • 951 • 87 -
zlab-princeton/Vero-600k
Viewer • Updated • 606k • 59.8k • 47
UniME-V2
-
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 12 -
TianchengGu/UniME-V2-LLaVA-OneVision-8B
Image-Text-to-Text • 8B • Updated • 25 • 2 -
TianchengGu/UniME-V2-Qwen2VL-7B
Image-Text-to-Text • 8B • Updated • 68 • 2 -
TianchengGu/UniME-V2-Qwen2VL-2B
Image-Text-to-Text • 2B • Updated • 101 • 3
UniME
-
DeepGlint-AI/UniME-Phi3.5-V-4.2B
Image-Text-to-Text • Updated • 396 • 7 -
DeepGlint-AI/UniME-LLaVA-OneVision-7B
Image-Text-to-Text • 8B • Updated • 35 • 3 -
DeepGlint-AI/UniME-LLaVA-1.6-7B
Image-Text-to-Text • 8B • Updated • 35 • 5 -
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
Paper • 2504.17432 • Published • 42
RealSyn Dataset
-
Kaichengalex/RealSyn100M
Viewer • Updated • 89.6M • 1.17k • 16 -
Kaichengalex/RealSyn15M
Viewer • Updated • 13.5M • 335 • 3 -
Kaichengalex/RealSyn30M
Viewer • Updated • 27M • 447 • 4 -
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm
Paper • 2502.12513 • Published • 16
SFT Dataset
decision-data
Ego
PreTraining
Robotic
Fully-Open
Multi-Image Dataset
GUI Dataset
OCR Dataset
UniME-R1
Doc Data
VideoDataset
CoT Dataset
-
opendatalab/ChartVerse-SFT-1.8M
Viewer • Updated • 1.88M • 4.98k • 141 -
OpenDataArena/MMFineReason-1.8M-Qwen3-VL-235B-Thinking
Viewer • Updated • 1.81M • 2.64k • 127 -
OpenDataArena/MMFineReason-SFT-123K-Qwen3-VL-235B-Thinking
Viewer • Updated • 123k • 951 • 87 -
zlab-princeton/Vero-600k
Viewer • Updated • 606k • 59.8k • 47
DanQing
Large-scale Chinese Image-Text Datasets
UniME-V2
-
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 12 -
TianchengGu/UniME-V2-LLaVA-OneVision-8B
Image-Text-to-Text • 8B • Updated • 25 • 2 -
TianchengGu/UniME-V2-Qwen2VL-7B
Image-Text-to-Text • 8B • Updated • 68 • 2 -
TianchengGu/UniME-V2-Qwen2VL-2B
Image-Text-to-Text • 2B • Updated • 101 • 3
RWKV-CLIP
UniME
-
DeepGlint-AI/UniME-Phi3.5-V-4.2B
Image-Text-to-Text • Updated • 396 • 7 -
DeepGlint-AI/UniME-LLaVA-OneVision-7B
Image-Text-to-Text • 8B • Updated • 35 • 3 -
DeepGlint-AI/UniME-LLaVA-1.6-7B
Image-Text-to-Text • 8B • Updated • 35 • 5 -
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
Paper • 2504.17432 • Published • 42
Web-Person Dataset
RealSyn Dataset
-
Kaichengalex/RealSyn100M
Viewer • Updated • 89.6M • 1.17k • 16 -
Kaichengalex/RealSyn15M
Viewer • Updated • 13.5M • 335 • 3 -
Kaichengalex/RealSyn30M
Viewer • Updated • 27M • 447 • 4 -
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm
Paper • 2502.12513 • Published • 16
Vision-Language Dataset
SFT Dataset
MLLM4Embedding
-
GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
Paper • 2412.16855 • Published • 5 -
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
Paper • 2410.05160 • Published • 4 -
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
Paper • 2507.04590 • Published • 17