Ningxin Peng

nxpeng9235's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted 2 papers 3 months ago

Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent

Paper • 2407.21646 • Published Jul 31 • 18

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning

Paper • 2407.18248 • Published Jul 25 • 30