Resources for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
Xin Lai
xinlai
AI & ML interests
Multimodal LLM, LLM Reasoning, Point Cloud Segmentation, Image Segmentation
Recent Activity
upvoted
a
paper
21 days ago
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
upvoted
a
paper
about 1 month ago
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Organizations
None yet
Collections
1
Papers
2
models
21
xinlai/Qwen2-7B-Instruct-Step-DPO
Text Generation
•
Updated
•
259
•
2
xinlai/Qwen2-57B-A14B-SFT-Step-DPO
Text Generation
•
Updated
•
26
•
1
xinlai/Qwen1.5-32B-SFT-Step-DPO
Text Generation
•
Updated
•
24
•
1
xinlai/Llama-3-70B-SFT-Step-DPO
Text Generation
•
Updated
•
29
xinlai/DeepSeekMath-Base-SFT-Step-DPO
Text Generation
•
Updated
•
30
xinlai/Qwen2-7B-SFT-Step-DPO
Text Generation
•
Updated
•
27
xinlai/Qwen2-72B-Instruct-Step-DPO
Text Generation
•
Updated
•
29
xinlai/DeepSeekMath-RL-Step-DPO
Text Generation
•
Updated
•
33
•
2
xinlai/Qwen2-57B-A14B-SFT
Text Generation
•
Updated
•
26
xinlai/Qwen1.5-32B-SFT
Text Generation
•
Updated
•
17