Picture for Chenyang Zhao

Chenyang Zhao

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Add code
Apr 09, 2024
Viaarxiv icon

YAYI 2: Multilingual Open-Source Large Language Models

Dec 22, 2023
Viaarxiv icon

Seam-guided local alignment and stitching for large parallax images

Add code
Nov 30, 2023
Viaarxiv icon

Large Language Model is a Good Policy Teacher for Training Reinforcement Learning Agents

Add code
Nov 29, 2023
Viaarxiv icon

TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise

Oct 31, 2023
Figure 1 for TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
Figure 2 for TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
Figure 3 for TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
Figure 4 for TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
Viaarxiv icon

Prompt2Model: Generating Deployable Models from Natural Language Instructions

Add code
Aug 23, 2023
Figure 1 for Prompt2Model: Generating Deployable Models from Natural Language Instructions
Figure 2 for Prompt2Model: Generating Deployable Models from Natural Language Instructions
Figure 3 for Prompt2Model: Generating Deployable Models from Natural Language Instructions
Figure 4 for Prompt2Model: Generating Deployable Models from Natural Language Instructions
Viaarxiv icon

Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach

Add code
Jun 11, 2023
Figure 1 for Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
Figure 2 for Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
Figure 3 for Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
Figure 4 for Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
Viaarxiv icon

Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization

May 06, 2023
Figure 1 for Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization
Figure 2 for Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization
Figure 3 for Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization
Figure 4 for Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization
Viaarxiv icon

ODAM: Gradient-based instance-specific visual explanations for object detection

Apr 13, 2023
Figure 1 for ODAM: Gradient-based instance-specific visual explanations for object detection
Figure 2 for ODAM: Gradient-based instance-specific visual explanations for object detection
Figure 3 for ODAM: Gradient-based instance-specific visual explanations for object detection
Figure 4 for ODAM: Gradient-based instance-specific visual explanations for object detection
Viaarxiv icon

On Context Distribution Shift in Task Representation Learning for Offline Meta RL

Add code
Apr 01, 2023
Figure 1 for On Context Distribution Shift in Task Representation Learning for Offline Meta RL
Figure 2 for On Context Distribution Shift in Task Representation Learning for Offline Meta RL
Figure 3 for On Context Distribution Shift in Task Representation Learning for Offline Meta RL
Figure 4 for On Context Distribution Shift in Task Representation Learning for Offline Meta RL
Viaarxiv icon