Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillationby Vasileios Tsouvalas, Aaqib Saeed, Tanir…
Routoo: Learning to Route to Large Language Models Effectivelyby Alireza Mohammadshahi, Arshad Rafiq Shaikh, Majid…
Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollersby Wei Tao, Shenglin He, Kai Lu, Xiaoyang…
Inference Attacks Against Face Recognition Model without Classification Layersby Yuanqing Huang, Huilong Chen, Yinggui Wang,…
A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)by Charles Meyers, Mohammad…
Embedding Attack Project (Work Report)by Jiameng Pu, Zafar TakhirovFirst submitted to arxiv on: 24 Jan…
MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakageby Ying…
Bayesian Semi-structured Subspace Inferenceby Daniel Dold, David Rügamer, Beate Sick, Oliver DürrFirst submitted to arxiv…
Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Controlby Yongjun Kim, Sejin Seo,…
BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Modelsby Feng Lin, Hanling Yi, Hongbin…