Multimodal models with leading performance.
AI & ML interests
Large Language Models
Recent Activity
View all activity
The MiniCPM family of LLMs and VLLMs.
The collection of open-source models that adopt Ultra Series datasets for training
CPM-Bee series models.
Parsing-free RAG supported by VLMs
-
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
Paper • 2410.10594 • Published • 29 -
openbmb/VisRAG-Ret
Feature Extraction • 3B • Updated • 2.86k • 70 -
openbmb/VisRAG-Ret-Train-Synthetic-data
Viewer • Updated • 239k • 1.88k • 11 -
openbmb/VisRAG-Ret-Train-In-domain-data
Viewer • Updated • 123k • 1.32k • 4
Multimodal models with leading performance.
MiniCPM4: Ultra-Efficient LLMs on End Devices
The MiniCPM family of LLMs and VLLMs.
Extrapolating RLVR to General Domains without Verifiers
The collection of open-source models that adopt Ultra Series datasets for training
UltraLM, UltraRM and UltraCM.
CPM-Bee series models.
Advancing LLM Reasoning Generalists with Preference Trees
Parsing-free RAG supported by VLMs
-
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
Paper • 2410.10594 • Published • 29 -
openbmb/VisRAG-Ret
Feature Extraction • 3B • Updated • 2.86k • 70 -
openbmb/VisRAG-Ret-Train-Synthetic-data
Viewer • Updated • 239k • 1.88k • 11 -
openbmb/VisRAG-Ret-Train-In-domain-data
Viewer • Updated • 123k • 1.32k • 4
Embedding, re-ranking, generation -- the cornerstone of RAG.