4 papers
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
Hao Li, Jingkun An, Zijun Song +8
Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax. Existing methods mitigate this by balancing dual object…
Encoder-Inverter Framework for Seismic Acoustic Impedance Inversion
Junheng Peng, Yingtian Liu, Xiaowen Wang +2
Seismic acoustic impedance inversion is a challenging problem in geophysical exploration, primarily due to the scarcity of well-logging data and the inherent nonlinearity of the ta…
The Nash-MTL-STCN Method For Prestack Three-Parameter Inversion
Yingtian Liu, Yong Li, Huating Li +3
Deep learning (DL) techniques have been widely used in prestack three-parameter inversion to address its ill-posed problems. Among these DL techniques, Multi-task learning (MTL) me…
Acoustic Impedance Prediction Using an Attention-Based Dual-Branch Double-Inversion Network
Wen Feng, Yong Li, Yingtian Liu +1
Seismic impedance inversion is a widely used technique for reservoir characterization. Accurate, high-resolution seismic impedance data form the foundation for subsequent reservoir…