feed-forward network

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models EMNLP 2024 F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation NAACL 2024 FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation ACL 2024 From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning NAACL 2024 How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers NeurIPS 2024 How do Large Language Models Handle Multilingualism? NeurIPS 2024 Interpretability-based Tailored Knowledge Editing in Transformers EMNLP 2024 Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis EMNLP 2024 iTransformer: Inverted Transformers Are Effective for Time Series Forecasting ICLR 2024 Language Models Implement Simple Word2Vec-style Vector Arithmetic NAACL 2024 LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models ICML 2024 Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning ICML 2024 Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing EMNLP 2024 Neuron-Level Knowledge Attribution in Large Language Models EMNLP 2024 Neurons in Large Language Models: Dead, N-gram, Positional ACL 2024 On Least Square Estimation in Softmax Gating Mixture of Experts ICML 2024 On the Diminishing Returns of Width for Continual Learning ICML 2024 PartialFormer: Modeling Part Instead of Whole for Machine Translation ACL 2024 PMET: Precise Model Editing in a Transformer AAAI 2024 Probing Large Language Models from a Human Behavioral Perspective COLING 2024 Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers (Student Abstract) AAAI 2024 SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds CVPR 2024 Splatter Image: Ultra-Fast Single-View 3D Reconstruction CVPR 2024 Testing the limits of logical reasoning in neural and hybrid models NAACL 2024 UltraSparseBERT: 99% Conditionally Sparse Language Modelling ACL 2024