Chenxi Wang

Aurora-cx's activity

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

upvoted a paper 6 days ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published 10 days ago • 24

upvoted a paper 8 months ago

Do LLMs "Feel"? Emotion Circuits Discovery and Control

Paper • 2510.11328 • Published Oct 13, 2025 • 8

upvoted 2 papers over 1 year ago

Autonomous Agents for Collaborative Task under Information Asymmetry

Paper • 2406.14928 • Published Jun 21, 2024 • 2

Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia

Paper • 2503.01714 • Published Mar 3, 2025 • 5