Cortex: Consolidating Context into Parametric Memory
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
-
zjunlp/LongDS
Viewer • Updated • 184 • 2.59k • 6 -
zjunlp/DataMind-Analysis-Qwen2.5-7B
Text Generation • 8B • Updated • 26 • 2 -
zjunlp/DataMind-Analysis-Qwen2.5-14B
Text Generation • 15B • Updated • 15 • 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 • 25 • 1 -
zjunlp/OceanGPT-basic-30B-A3B-Thinking
Text Generation • 31B • Updated • 22 • 1 -
zjunlp/OceanGPT-basic-4B-Instruct
Text Generation • 4B • Updated • 24 • 1 -
zjunlp/OceanGPT-basic-4B-Thinking
Text Generation • 4B • Updated • 24 • 1
Benchmarking Agentic Workflow Generation
Data and models for Mol-Instructions.
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following
-
zjunlp/LabVLA-5B-Base
Robotics • 5B • Updated • 77 • 36 -
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
Paper • 2606.13578 • Published • 64 -
LabVLA
🧪1VLA model for scientific laboratory robotics
-
zjunlp/LabUtopia-Level3-TransportBeaker
Franka Panda • Updated • 100 episodes • 442 • 3
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.
Cortex: Consolidating Context into Parametric Memory
-
zjunlp/LongDS
Viewer • Updated • 184 • 2.59k • 6 -
zjunlp/DataMind-Analysis-Qwen2.5-7B
Text Generation • 8B • Updated • 26 • 2 -
zjunlp/DataMind-Analysis-Qwen2.5-14B
Text Generation • 15B • Updated • 15 • 2 -
Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study
Paper • 2506.19794 • Published • 8
-
zjunlp/LabVLA-5B-Base
Robotics • 5B • Updated • 77 • 36 -
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
Paper • 2606.13578 • Published • 64 -
LabVLA
🧪1VLA model for scientific laboratory robotics
-
zjunlp/LabUtopia-Level3-TransportBeaker
Franka Panda • Updated • 100 episodes • 442 • 3
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 • 25 • 1 -
zjunlp/OceanGPT-basic-30B-A3B-Thinking
Text Generation • 31B • Updated • 22 • 1 -
zjunlp/OceanGPT-basic-4B-Instruct
Text Generation • 4B • Updated • 24 • 1 -
zjunlp/OceanGPT-basic-4B-Thinking
Text Generation • 4B • Updated • 24 • 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