view article Article GLM-5: China's First Public AI Company Ships a Frontier Model mlabonne • Feb 17 • 3
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks Paper • 2606.03458 • Published Jun 2 • 67
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights Paper • 2509.22944 • Published Sep 26, 2025 • 80