5 papers · 1 filter
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
Qifan Yu, Xinyu Ma, Zhijian Zhuo +7
Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively explored depth expansion, width expansio…
Theoretical Benefit and Limitation of Diffusion Language Model
Guhao Feng, Yihan Geng, Jian Guan +3
Diffusion language models have emerged as a promising approach for text generation. One would naturally expect this method to be an efficient replacement for autoregressive models…
DPO Meets PPO: Reinforced Token Optimization for RLHF
Han Zhong, Zikang Shan, Guhao Feng +6
In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards -- a chall…
Do Efficient Transformers Really Save Computation?
Kai Yang, Jan Ackermann, Zhenyu He +6
As transformer-based language models are trained on increasingly large datasets and with vast numbers of parameters, finding more efficient alternatives to the standard Transformer…
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
Zhenyu He, Guhao Feng, Shengjie Luo +6
In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE). For each position,…