training time reduction

5 papers

• Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
• FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
• On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
• You Only Spectralize Once: Taking a Spectral Detour to Accelerate Graph Neural Network