Qingsong Wen

5 papers Head of AI Research @ Squirrel AI

• Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
• Improving Bilinear RNN with Closed-loop Control
• Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
• SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
• ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models