7 papers · 1 filter
TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation
Daiye Miao, Yufang Liu, Jie Wang +6
LoRA has become one of the most widely used parameter-efficient fine-tuning methods due to its simplicity and effectiveness. However, numerous studies have shown that LoRA often in…
DVAGen: Dynamic Vocabulary Augmented Generation
Wei Du, Nuowei Liu, Jie Wang +4
Language models trained with a fixed vocabulary struggle to generalize to novel or out-of-vocabulary words, limiting their flexibility in handling diverse token combinations. Exist…
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
Tao Ji, Bin Guo, Yuanbin Wu +6
Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Val…
On Support Samples of Next Word Prediction
Yuqian Li, Yupei Du, Yufang Liu +3
Language models excel in various tasks by making complex decisions, yet understanding the rationale behind these decisions remains a challenge. This paper investigates \emph{data-c…
AntLM: Bridging Causal and Masked Language Models
Xinru Yu, Bin Guo, Shiwei Luo +3
Causal Language Modeling (CLM) and Masked Language Modeling (MLM) are two mainstream learning paradigms based on Transformer networks, specifically the Decoder-only and Encoder-onl…
Generation with Dynamic Vocabulary
Yanting Liu, Tao Ji, Changzhi Sun +2
We introduce a new dynamic vocabulary for language models. It can involve arbitrary text spans during generation. These text spans act as basic generation bricks, akin to tokens in…