conftrace_

feed-forward network

79 papers

Explore in graph

Also known as

FFN

Co-occurring keywords

large language model (13587) neural network (6616) model compression (3302) attention mechanism (4001) transformer architecture (1560) mixture of expert (640) image generation (2073) parameter efficiency (417) parameter-efficient fine-tuning (736) language model (4599)

Papers

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
PartialFormer: Modeling Part Instead of Whole for Machine Translation ACL 2024
Neuron-Level Knowledge Attribution in Large Language Models EMNLP 2024
Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis EMNLP 2024
Interpretability-based Tailored Knowledge Editing in Transformers EMNLP 2024
CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification EMNLP 2024
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models EMNLP 2024
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers NIPS 2024
Enhancing Parameter-efficient Fine-tuning with Simple Calibration Based on Stable Rank COLING 2024
Probing Large Language Models from a Human Behavioral Perspective COLING 2024
ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks NIPS 2024
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning NAACL 2024
F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation NAACL 2024
Testing the limits of logical reasoning in neural and hybrid models NAACL 2024
PMET: Precise Model Editing in a Transformer AAAI 2024
Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis EACL 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
Brainformers: Trading Simplicity for Efficiency ICML 2023
Unveiling Multilinguality in Transformer Models: Exploring Language Specificity in Feed-Forward Networks EMNLP 2023
Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring CVPR 2023
Go Wider Instead of Deeper AAAI 2022
Associating Objects and Their Effects in Video through Coordination Games NIPS 2022
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space EMNLP 2022