AI & ML interests
A research group from Zhejiang University working on KG and NLP Technologies
Recent Activity
View all activity
Papers
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
A Large-Scale Multimodal Ocean Corpus for Foundation Models
model adapter weight and train data for "Agent Planning with World Knowledge Model"
Merged models generated for the model kinship paper.
-
zjunlp/LongDS
Viewer • Updated • 184 • 15.5k • 5 -
zjunlp/DataMind-Analysis-Qwen2.5-7B
Text Generation • 8B • Updated • 34 • 2 -
zjunlp/DataMind-Analysis-Qwen2.5-14B
Text Generation • 15B • Updated • 16 • 2 -
Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study
Paper • 2506.19794 • Published • 8
Official Skills, graphs, experiment results, and runtime logs for SkillNet-Fabric.
-
zjunlp/OceanGPT-basic-30B-A3B-Instruct
Text Generation • 31B • Updated • 27 • 1 -
zjunlp/OceanGPT-basic-30B-A3B-Thinking
Text Generation • 31B • Updated • 20 • 1 -
zjunlp/OceanGPT-basic-4B-Instruct
Text Generation • 4B • Updated • 29 • 1 -
zjunlp/OceanGPT-basic-4B-Thinking
Text Generation • 4B • Updated • 23 • 1
Benchmarking Agentic Workflow Generation
Data and models for Mol-Instructions.
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following
-
zjunlp/LongDS
Viewer • Updated • 184 • 15.5k • 5 -
zjunlp/DataMind-Analysis-Qwen2.5-7B
Text Generation • 8B • Updated • 34 • 2 -
zjunlp/DataMind-Analysis-Qwen2.5-14B
Text Generation • 15B • Updated • 16 • 2 -
Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study
Paper • 2506.19794 • Published • 8
A Large-Scale Multimodal Ocean Corpus for Foundation Models
Official Skills, graphs, experiment results, and runtime logs for SkillNet-Fabric.
-
zjunlp/OceanGPT-basic-30B-A3B-Instruct
Text Generation • 31B • Updated • 27 • 1 -
zjunlp/OceanGPT-basic-30B-A3B-Thinking
Text Generation • 31B • Updated • 20 • 1 -
zjunlp/OceanGPT-basic-4B-Instruct
Text Generation • 4B • Updated • 29 • 1 -
zjunlp/OceanGPT-basic-4B-Thinking
Text Generation • 4B • Updated • 23 • 1
Benchmarking Agentic Workflow Generation
model adapter weight and train data for "Agent Planning with World Knowledge Model"
Merged models generated for the model kinship paper.
Data and models for Mol-Instructions.
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following