Picture for Yonggang Jin

Yonggang Jin

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning

Mar 26, 2024
Figure 1 for COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
Figure 2 for COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
Figure 3 for COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
Figure 4 for COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
Viaarxiv icon

Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction

Add code
Feb 08, 2024
Viaarxiv icon

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Add code
Nov 30, 2023
Viaarxiv icon

Deep Reinforcement Learning with Multitask Episodic Memory Based on Task-Conditioned Hypernetwork

Add code
Jun 21, 2023
Figure 1 for Deep Reinforcement Learning with Multitask Episodic Memory Based on Task-Conditioned Hypernetwork
Figure 2 for Deep Reinforcement Learning with Multitask Episodic Memory Based on Task-Conditioned Hypernetwork
Figure 3 for Deep Reinforcement Learning with Multitask Episodic Memory Based on Task-Conditioned Hypernetwork
Figure 4 for Deep Reinforcement Learning with Multitask Episodic Memory Based on Task-Conditioned Hypernetwork
Viaarxiv icon