SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
Paper • 2512.04746 • Published • 14
Heng Guo
n1ck-guo
AI & ML interests
None yet
Recent Activity
updated a dataset about 3 hours ago
Intel/ld_requests updated a dataset about 1 month ago
Intel/dynamic_model_information updated a model about 2 months ago
Intel/gemma-4-26B-A4B-it-int4-mixed-AutoRoundOrganizations
authored a
paper 5 months ago