Summary of Mpq-diff: Mixed Precision Quantization For Diffusion Models, by Rocco Manz Maruzzelli et al.
MPQ-Diff: Mixed Precision Quantization for Diffusion Modelsby Rocco Manz Maruzzelli, Basile Lewandowski, Lydia Y. ChenFirst…
MPQ-Diff: Mixed Precision Quantization for Diffusion Modelsby Rocco Manz Maruzzelli, Basile Lewandowski, Lydia Y. ChenFirst…
COAP: Memory-Efficient Training with Correlation-Aware Gradient Projectionby Jinqi Xiao, Shen Sang, Tiancheng Zhi, Jing Liu,…
Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendationby Siqing Zhang, Yuchen Ding, Wei…
DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decodingby Jungbin Cho, Junwan Kim, Jisoo…
On the effectiveness of discrete representations in sparse mixture of expertsby Giang Do, Kha Pham,…
FAMES: Fast Approximate Multiplier Substitution for Mixed-Precision Quantized DNNs–Down to 2 Bits!by Yi Ren, Ruge…
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokensby Xu…
Pushing the Limits of Large Language Model Quantization via the Linearity Theoremby Vladimir Malinovskii, Andrei…
Lion Cub: Minimizing Communication Overhead in Distributed Lionby Satoki Ishikawa, Tal Ben-Nun, Brian Van Essen,…
Representation Collapsing Problems in Vector Quantizationby Wenhao Zhao, Qiran Zou, Rushi Shah, Dianbo LiuFirst submitted…