From the 1 of 9 linked papers with an AI index.
5 papers · 1 filter
SandwichQuant: Which Parameters Matter Before and After Quantization?
Peng Xia, Junbiao Pang
Quantization correction methods usually optimize weights, quantization parameters, or reconstruction objectives, while the underlying parameter subspaces responsible for effective…
Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization
Peng Xia, Junbiao Pang, Zheng Huang
Low-bit quantization suffers severe accuracy degradation on compact networks, rooted in the dominant full-parameter coupled training paradigm that ignores parameter subspace hetero…
Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models
Peng Xia, Junbiao Pang, Muhammad Ayub Sabir
The paper introduces Efficient Tuning Before Quantization (ETBQ), a lightweight pre‑conditioning step that adjusts a full‑precision model using perturbations from quantization erro…
UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding
Yueming Xu, Jiahui Zhang, Ze Huang +12
Despite the impressive progress on understanding and generating images shown by the recent unified architectures, the integration of 3D tasks remains challenging and largely unexpl…
Efficiently Training A Flat Neural Network Before It has been Quantizated
Peng Xia, Junbiao Pang, Tianyang Cai
Post-training quantization (PTQ) for vision transformers (ViTs) has garnered significant attention due to its efficiency in compressing models. However, existing methods typically…