Papers with ReLU
Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks (2026.acl-short)
Copied to clipboard
| Challenge: | Xiao et al., 2024) show that softmax models display an attention sink . he argues that normalization over a probability simplex must force attention to collapse onto a stable anchor to realize a default state. |
| Approach: | They show that normalization over a trigger-conditional behavior *necessarily* induces a sink in softmax self-attention models. |
| Outcome: | The proposed model can solve a task with no sink in softmax models. |
CRYPTOGRU: Low Latency Privacy-Preserving Text Analysis With GRU (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to combine HE and GC in RNNs suffer from long inference latency due to the slow activation functions. |
| Approach: | They propose a hybrid structure of HE and GC gated recurrent unit network, for low-latency secure inferences. |
| Outcome: | The proposed structure improves the secure inference latency by up to 138 over one of the state-of-the-art secure networks on the Penn Treebank dataset. |
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models (2025.coling-main)
Copied to clipboard
Chenyang Song, Xu Han, Zhengyan Zhang, Shengding Hu, Xiyu Shi, Kuai Li, Chen Chen, Zhiyuan Liu, Guangli Li, Tao Yang, Maosong Sun
| Challenge: | Activation sparsity is a promising paradigm for accelerating model inference . few large language models achieve high activation spar and comparable performance . |
| Approach: | They propose a method to achieve activation sparsity and acceleration in large language models . they introduce ReLU activation and adopt progressive sparse regularization . |
| Outcome: | The proposed method achieves high activation sparsity and comparable model performance. |
DROWN: Towards Tighter LiRPA-based Robustness Certification (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for certifying the robustness of deep neural networks suffer from precision or scalability issues. |
| Approach: | They propose a method to certify the robustness of deep neural networks . they propose to use two pairs of linear bounds to refine pre-activation bounds . |
| Outcome: | The proposed method achieves higher certified robustness than the baseline on CNNs and 4.68 times larger certified radii than the Transformers. |
Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks (D18-1)
Copied to clipboard
| Challenge: | Activation functions are nonlinearities which have been attributed to the success story of deep learning. |
| Approach: | They propose to use a penalized tanh function to replace the sigmoid and tansh gates in LSTM cells and to improve the performance of the activation function. |
| Outcome: | The proposed activation function performs best on all tasks and can replace the sigmoid and tanh gates in LSTM cells. |
Sparse Attention with Linear Units (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have suggested that sparse attention mechanisms can be made more interpretable by replacing the softmax activation with its sparser variants. |
| Approach: | They propose a method to replace softmax activation with a ReLU to achieve sparsity in attention by layer normalization with either a specialized initialization or an additional gating function. |
| Outcome: | The proposed model is easy to implement and more efficient than previously proposed sparse attention mechanisms. |
Local Interpretation of Transformer Based on Linear Decomposition (2023.acl-long)
Copied to clipboard
| Challenge: | Existing work on local explanation generation attempts to understand model dynamics on word-level or phraselevel by assigning importance scores on input features. |
| Approach: | They propose to interpret neural networks by linear decomposition by a Transformer model on a single input and a linear decomposing of the output to generate local explanations. |
| Outcome: | The proposed method achieves competitive performance in sentiment classification and machine translation, and fidelity of explanation. |