information flow

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing NeurIPS 2024 Layer Collaboration in the Forward-Forward Algorithm AAAI 2024 Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers ICML 2024 SparseFlow: Accelerating Transformers by Sparsifying Information Flows ACL 2024 Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models EMNLP 2024 Dissecting Recall of Factual Associations in Auto-Regressive Language Models EMNLP 2023 Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning EMNLP 2023 Test Coverage for Network Configurations NSDI 2023 VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers EMNLP 2023 Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup EMNLP 2022 Elastic-Link for Binarized Neural Networks AAAI 2022 Architecture Disentanglement for Deep Neural Networks ICCV 2021 Can Information Flows Suggest Targets for Interventions in Neural Circuits? NeurIPS 2021 Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances ACL 2021 How Does Topology Influence Gradient Propagation and Model Performance of Deep Networks With DenseNet-Type Skip Connections? CVPR 2021 Influence Patterns for Explaining Information Flow in BERT NeurIPS 2021 Progressive Multi-task Learning with Controlled Information Flow for Joint Entity and Relation Extraction AAAI 2021 Screening Gender Transfer in Neural Machine Translation EMNLP 2021 SURPRISE! and When to Schedule It. IJCAI 2021 Towards a Model-Theoretic View of Narratives NAACL 2021 Heterogeneous Knowledge Distillation Using Information Flow Modeling CVPR 2020 Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules ICML 2020 Quantifying Attention Flow in Transformers ACL 2020 Semi-Modular Inference: enhanced learning in multi-modular models by tempering the influence of components AISTATS 2020 Reading selectively via Binary Input Gated Recurrent Unit IJCAI 2019