KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks Paper • 2606.03458 • Published 4 days ago • 49
SINQ Collection This collection contains the models quantized with the SINQ quantization method. • 19 items • Updated Nov 24, 2025 • 10
AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs Paper • 2505.11557 • Published May 15, 2025 • 7