Memory Faults in Activation-sparse Quantized Deep Neural Networks: Analysis and Mitigation using Sharpness-aware Trainingby Akul…
Improving the Validity and Practical Usefulness of AI/ML Evaluations Using an Estimands Frameworkby Olivier Binette,…
MiNT: Multi-Network Training for Transfer Learning on Temporal Graphsby Kiarash Shamsi, Tran Gia Bao Ngo,…
CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inferenceby Shayan Shekarforoush, David B. Lindell, Marcus…
Semantic Membership Inference Attack against Large Language Modelsby Hamid Mozaffari, Virendra J. MaratheFirst submitted to…
Flextron: Many-in-One Flexible Large Language Modelby Ruisi Cai, Saurav Muralidharan, Greg Heinrich, Hongxu Yin, Zhangyang…
ECGMamba: Towards Efficient ECG Classification with BiSSMby Yupeng Qiang, Xunde Dong, Xiuling Liu, Yang Yang,…
QQQ: Quality Quattuor-Bit Quantization for Large Language Modelsby Ying Zhang, Peng Zhang, Mincong Huang, Jingyang…
Neural Concept Binderby Wolfgang Stammer, Antonia Wüst, David Steinmann, Kristian KerstingFirst submitted to arxiv on:…
Deep Symbolic Optimization for Combinatorial Optimization: Accelerating Node Selection by Discovering Potential Heuristicsby Hongyu Liu,…