Quantization | JJ's Blog

📝 TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization - ICML'26

📝 DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization - NeurIPS'25

📝 SPINQUANT: LLM QUANTIZATION WITH LEARNED ROTATIONS - ICLR'25

📝 QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models - NeurIPS'25 Spotlight