Convex Distillation: Efficient Compression of Deep Networks via Convex Optimizationby Prateek Varshney, Mert PilanciFirst submitted…
Mixture Compressor for Mixture-of-Experts LLMs Gains Moreby Wei Huang, Yue Liao, Jianhui Liu, Ruifei He,…
Mastering Chinese Chess AI (Xiangqi) Without Searchby Yu Chen, Juntong Lin, Zhichao ShuFirst submitted to…
Language Model-Driven Data Pruning Enables Efficient Active Learningby Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha…
LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversityby Selim Furkan Tekin, Fatih Ilhan, Tiansheng Huang, Sihao…
Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generationby Rohin Manvi,…
Personalized Federated Learning for Generative AI-Assisted Semantic Communicationsby Yubo Peng, Feibo Jiang, Li Dong, Kezhi…
RelChaNet: Neural Network Feature Selection using Relative Change Scoresby Felix ZimmerFirst submitted to arxiv on:…
Review Non-convex Optimization Method for Machine Learningby Greg B Fotopoulos, Paul Popovich, Nicholas Hall PapadopoulosFirst…
DRUPI: Dataset Reduction Using Privileged Informationby Shaobo Wang, Yantai Yang, Shuaiyu Zhang, Chenghao Sun, Weiya…