Project Tracyn: Generative Artificial Intelligence based Peripherals Trace Synthesizerby Zhibai Huang, Yihan Shen, Yongchen Xie,…
Neuro-Symbolic Rule Listsby Sascha Xu, Nils Philipp Walter, Jilles VreekenFirst submitted to arxiv on: 10…
Beyond Toxic Neurons: A Mechanistic Analysis of DPO for Toxicity Reductionby Yushi Yang, Filip Sondej,…
Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimatorby Kazuki Fujii, Kohei…
Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Boundsby Mehdi Hennequin, Abdelkrim Zitouni, Khalid…
Online Parallel Multi-Task Relationship Learning via Alternating Direction Method of Multipliersby Ruiyu Li, Peilin Zhao,…
Mutual-energy inner product optimization method for constructing feature coordinates and image classification in Machine Learningby…
Poor Man’s Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approachby Yequan Zhao, Hai Li, Ian…
Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularizationby Zhuotong Chen, Fang Liu,…
Continuous-Time Analysis of Adaptive Optimization and Normalizationby Rhys Gould, Hidenori TanakaFirst submitted to arxiv on:…