Academic

Academic

Academic · 1 min

DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression

arXiv:2603.22324v1 Announce Type: new Abstract: We introduce Delta-Aware Quantization (DAQ), a data-free post-training quantization framework that preserves the knowledge acquired during post-training. Standard quantization objectives …

Xiaoming Yu, Shize Tang, Guanghua Yu, Linchuan Xie, Song Liu, Jianchen Zhu, Feng Li
0 views
Academic · 1 min

Hybrid Associative Memories

arXiv:2603.22325v1 Announce Type: new Abstract: Recurrent neural networks (RNNs) and self-attention are both widely used sequence-mixing layers that maintain an internal memory. However, this memory …

Leon Lufkin, Tom\'as Figliolia, Beren Millidge, Kamesh Krishnamurthy
0 views
Academic · 1 min

Beyond the Mean: Distribution-Aware Loss Functions for Bimodal Regression

arXiv:2603.22328v1 Announce Type: new Abstract: Despite the strong predictive performance achieved by machine learning models across many application domains, assessing their trustworthiness through reliable estimates …

Abolfazl Mohammadi-Seif, Carlos Soares, Rita P. Ribeiro, Ricardo Baeza-Yates
8 views
Academic · 1 min

Trained Persistent Memory for Frozen Decoder-Only LLMs

arXiv:2603.22329v1 Announce Type: new Abstract: Decoder-only language models are stateless: hidden representations are discarded after every forward pass and nothing persists across sessions. Jeong (2026a) …

Hong Jeong
0 views