Understanding the difficulty of low-precision post-training quantization of large language modelsby Zifei Xu, Sayeh Sharify,…
Measuring Diversity: Axioms and Challengesby Mikhail Mironov, Liudmila ProkhorenkovaFirst submitted to arxiv on: 18 Oct…
MomentumSMoE: Integrating Momentum into Sparse Mixture of Expertsby Rachel S.Y. Teo, Tan M. NguyenFirst submitted…
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstructionby Manuel Brenner, Christoph Jürgen…
G-NeuroDAVIS: A Neural Network model for generalized embedding, data visualization and sample generationby Chayan Maitra,…
Formal Explanations for Neuro-Symbolic AIby Sushmita Paul, Jinqiang Yu, Jip J. Dekker, Alexey Ignatiev, Peter…
Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplersby Runjia Li, Qiwei Di, Quanquan…
Pseudo-label Refinement for Improving Self-Supervised Learning Systemsby Zia-ur-Rehman, Arif Mahmood, Wenxiong KangFirst submitted to arxiv…
RAZOR: Refining Accuracy by Zeroing Out Redundanciesby Daniel Riccio, Genoveffa Tortora, Mara SangiovanniFirst submitted to…
MoDification: Mixture of Depths Made Easyby Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu…