Xin Lai's picture

6 5 1

Xin Lai

xinlai

·

x-lai

AI & ML interests

Multimodal LLM, LLM Reasoning, Point Cloud Segmentation, Image Segmentation

Recent Activity

upvoted a paper 9 days ago

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

upvoted a paper 4 months ago

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

upvoted a paper 4 months ago

VisionZip: Longer is Better but Not Necessary in Vision Language Models

View all activity

Organizations

None yet

xinlai's activity

upvoted a paper 9 days ago

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Paper • 2503.18892 • Published 10 days ago • 27

upvoted 2 papers 4 months ago

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Paper • 2412.09501 • Published Dec 12, 2024 • 48

VisionZip: Longer is Better but Not Necessary in Vision Language Models

Paper • 2412.04467 • Published Dec 5, 2024 • 110

upvoted 2 papers 9 months ago

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Paper • 2402.03300 • Published Feb 5, 2024 • 112

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Paper • 2406.18629 • Published Jun 26, 2024 • 42