VisionZip: Longer is Better but Not Necessary in Vision Language Models Paper • 2412.04467 • Published Dec 5, 2024 • 105
VisionZip: Longer is Better but Not Necessary in Vision Language Models Paper • 2412.04467 • Published Dec 5, 2024 • 105
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Paper • 2406.18629 • Published Jun 26, 2024 • 41
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Paper • 2406.18629 • Published Jun 26, 2024 • 41