hidden state

Separations in the Representational Capabilities of Transformers and Recurrent Architectures NeurIPS 2024 Transformers Represent Belief State Geometry in their Residual Stream NeurIPS 2024 Understanding and Patching Compositional Reasoning in LLMs ACL 2024 Vision Mamba Mender NeurIPS 2024 Balaur: Language Model Pretraining with Lexical Semantic Relations EMNLP 2023 Counterfactual Analysis in Dynamic Latent State Models ICML 2023 Dynamical Linear Bandits ICML 2023 Mitigating Artifacts in Real-World Video Super-resolution Models AAAI 2023 PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism ACL 2023 Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions ACL 2023 VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers EMNLP 2023 Anticipation-Free Training for Simultaneous Machine Translation ACL 2022 Garden Path Traversal in GPT-2 EMNLP 2022 Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning EMNLP 2022 On the Symmetries of Deep Learning Models and their Internal Representations NeurIPS 2022 Towards a Unified View of Parameter-Efficient Transfer Learning ICLR 2022 You Don’t Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers’ Private Personas NAACL 2022 Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies ICLR 2021 Learning and Generalization in RNNs NeurIPS 2021 Lipschitz Recurrent Neural Networks ICLR 2021 Liquid Time-constant Networks AAAI 2021 Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path ACL 2021 Practical Real Time Recurrent Learning with a Sparse Approximation ICLR 2021 Reconsidering the Past: Optimizing Hidden States in Language Models EMNLP 2021 RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting ICML 2021