2 papers
cs.CL2024
Semformer: Transformer Language Models with Semantic Planning
Yongjing Yin, Junran Ding, Kai Song +1
Next-token prediction serves as the dominant component in current neural language models. During the training phase, the model employs teacher forcing, which predicts tokens based…
cs.CR2024
NTTSuite: Number Theoretic Transform Benchmarks for Accelerating Encrypted Computation
Juran Ding, Yuanzhe Liu, Lingbin Sun +1
Privacy concerns have thrust privacy-preserving computation into the spotlight. Homomorphic encryption (HE) is a cryptographic system that enables computation to occur directly on…