feed-forward network

Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers NeurIPS 2024 Vision Transformers as Probabilistic Expansion from Learngene ICML 2024 WaveMo: Learning Wavefront Modulations to See Through Scattering CVPR 2024 Blockwise Parallel Transformers for Large Context Models NeurIPS 2023 Brainformers: Trading Simplicity for Efficiency ICML 2023 Brain-like representational straightening of natural movies in robust feedforward neural networks ICLR 2023 CoLT5: Faster Long-Range Transformers with Conditional Computation EMNLP 2023 Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring CVPR 2023 End-to-End Learning to Warm-Start for Real-Time Quadratic Optimization L4DC 2023 Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment EMNLP 2023 LookupFFN: Making Transformers Compute-lite for CPU inference ICML 2023 Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models’ Memories ACL 2023 MSCFFN: A New FFN with Multi-Space Cross to Accelerate Transformer EMNLP 2023 Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation ICCV 2023 One Wide Feedforward Is All You Need EMNLP 2023 Representational Strengths and Limitations of Transformers NeurIPS 2023 Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity NeurIPS 2023 Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis EACL 2023 Transformer-Patcher: One Mistake Worth One Neuron ICLR 2023 Unveiling Multilinguality in Transformer Models: Exploring Language Specificity in Feed-Forward Networks EMNLP 2023 Associating Objects and Their Effects in Video through Coordination Games NeurIPS 2022 Deep Sparse Conformer for Speech Recognition Interspeech 2022 Go Wider Instead of Deeper AAAI 2022 MoEfication: Transformer Feed-forward Layers are Mixtures of Experts ACL 2022 Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space EMNLP 2022