Papers with long-sequence modeling
LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering (2025.acl-short)
Copied to clipboard
Zhifan Ye, Zheng Wang, Kejing Xia, Jihoon Hong, Leshu Li, Lexington Whalen, Cheng Wan, Yonggan Fu, Yingyan Celine Lin, Souvik Kundu
| Challenge: | Recent work attributes performance degradation to an exponential decay in hidden-state memory. |
| Approach: | They propose a token filtering strategy that is training-free and attention-guided . they propose 'LAMB' to preserve critical tokens during inference . |
| Outcome: | The proposed token filtering improves long-context performance by 30.35% over state-of-the-art methods on benchmarks. |
A Survey of Retentive Network (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on the effectiveness of the Retentive Networks have not yet been conducted. |
| Approach: | They propose a retention mechanism that integrates the inductive bias of recurrent neural networks with the parallelizable training advantages of attention-based models. |
| Outcome: | The proposed retention mechanism combines the inductive bias of recurrent neural networks with the parallelizable training advantages of attention-based models. |
An Exploration of Mamba for Speech Self-Supervised Models (2026.acl-long)
Copied to clipboard
Tzu-Quan Lin, Heng-Cheng Kuo, Tzu-Chieh Wei, Hsi-Chun Cheng, Chun Wei Chen, Hsien-Fu Hsiao, Yu Tsao, Hung-yi Lee
| Challenge: | Mamba-based SSL models are promising for long-sequence modeling, speech unit extraction, and speech self-supervised learning. |
| Approach: | They propose to use Mamba-based HuBERT models as an alternative to Transformer-based SSL architectures. |
| Outcome: | The proposed models outperform Transformer-based models in language modeling tasks while showing superior performance on streaming ASR. |
Long Sequence Modeling with Attention Tensorization: From Sequence to Tensor Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a lack of attention-based models for long sequences poses challenges for long-sequence modeling . attention tensorization can be used to extend context lengths with improved efficiency . tenorization enables training of LLMs with context length longer than those trained on . |
| Approach: | They propose to tensorize long input sequences into compact tenses followed by attention on each transformed dimension. |
| Outcome: | The proposed model can be used as efficient transformer backbones to extend input context length with improved memory and time efficiency. |