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
10 days ago
VisionThink: Smart and Efficient Vision Language Model via Reinforcement
Learning
upvoted
a
paper
17 days ago
Scaling RL to Long Videos
upvoted
a
paper
about 1 month ago
MMSearch-R1: Incentivizing LMMs to Search
Organizations
None yet
models
21
xinlai/Qwen2-7B-Instruct-Step-DPO
Text Generation
•
8B
•
Updated
•
20
•
3
xinlai/Qwen2-57B-A14B-SFT-Step-DPO
Text Generation
•
57B
•
Updated
•
5
•
1
xinlai/Qwen1.5-32B-SFT-Step-DPO
Text Generation
•
33B
•
Updated
•
4
•
1
xinlai/Llama-3-70B-SFT-Step-DPO
Text Generation
•
71B
•
Updated
•
4
xinlai/DeepSeekMath-Base-SFT-Step-DPO
Text Generation
•
7B
•
Updated
•
11
xinlai/Qwen2-7B-SFT-Step-DPO
Text Generation
•
8B
•
Updated
•
23
xinlai/Qwen2-72B-Instruct-Step-DPO
Text Generation
•
73B
•
Updated
•
4
xinlai/DeepSeekMath-RL-Step-DPO
Text Generation
•
7B
•
Updated
•
6
•
2
xinlai/Qwen2-57B-A14B-SFT
Text Generation
•
57B
•
Updated
•
3
xinlai/Qwen1.5-32B-SFT
Text Generation
•
33B
•
Updated
•
3