Picture for Hassan Mansoor

Hassan Mansoor

VQA Training Sets are Self-play Environments for Generating Few-shot Pools

Add code
May 30, 2024
Figure 1 for VQA Training Sets are Self-play Environments for Generating Few-shot Pools
Figure 2 for VQA Training Sets are Self-play Environments for Generating Few-shot Pools
Figure 3 for VQA Training Sets are Self-play Environments for Generating Few-shot Pools
Figure 4 for VQA Training Sets are Self-play Environments for Generating Few-shot Pools
Viaarxiv icon

Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs

Add code
Mar 19, 2024
Figure 1 for Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs
Figure 2 for Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs
Figure 3 for Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs
Figure 4 for Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs
Viaarxiv icon

PERL: Parameter Efficient Reinforcement Learning from Human Feedback

Add code
Mar 15, 2024
Figure 1 for PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Figure 2 for PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Figure 3 for PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Figure 4 for PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Viaarxiv icon

ScreenAI: A Vision-Language Model for UI and Infographics Understanding

Add code
Feb 19, 2024
Viaarxiv icon

LLMs cannot find reasoning errors, but can correct them!

Add code
Nov 14, 2023
Viaarxiv icon

The Impact of Preference Agreement in Reinforcement Learning from Human Feedback: A Case Study in Summarization

Add code
Nov 02, 2023
Figure 1 for The Impact of Preference Agreement in Reinforcement Learning from Human Feedback: A Case Study in Summarization
Figure 2 for The Impact of Preference Agreement in Reinforcement Learning from Human Feedback: A Case Study in Summarization
Figure 3 for The Impact of Preference Agreement in Reinforcement Learning from Human Feedback: A Case Study in Summarization
Figure 4 for The Impact of Preference Agreement in Reinforcement Learning from Human Feedback: A Case Study in Summarization
Viaarxiv icon

RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Add code
Sep 01, 2023
Figure 1 for RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Figure 2 for RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Figure 3 for RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Figure 4 for RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Viaarxiv icon