model architecture

324 papers

Explore in graph

Co-occurring keywords

neural network (6616) convolutional neural network (4216) vision transformer (1091) image classification (1943) neural architecture search (665) neural network optimization (1293) efficient computing (779) model compression (3283) attention mechanism (3975) deep learning (2111)

Papers

VISPool: Enhancing Transformer Encoders with Vector Visibility Graph Neural Networks ACL 2024

Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives ACL 2024

Understanding the Gains from Repeated Self-Distillation NIPS 2024

Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement INTERSPEECH 2024

Harder Task Needs More Experts: Dynamic Routing in MoE Models ACL 2024

START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation NIPS 2024

Data Driven Threshold and Potential Initialization for Spiking Neural Networks AISTATS 2024

MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts NIPS 2024

Interface Design for Self-Supervised Speech Models INTERSPEECH 2024

HybridBERT - Making BERT Pretraining More Efficient Through Hybrid Mixture of Attention Mechanisms NAACL 2024

Modeling Overregularization in Children with Small Language Models ACL 2024

Puer at SemEval-2024 Task 2: A BioLinkBERT Approach to Biomedical Natural Language Inference NAACL 2024

OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer INTERSPEECH 2024

GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs CVPR 2024

RepViT: Revisiting Mobile CNN From ViT Perspective CVPR 2024

Conformer without Convolutions INTERSPEECH 2024

How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers NIPS 2024

Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing? ACL 2024

Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation NIPS 2023

Network Expansion for Practical Training Acceleration CVPR 2023

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations NIPS 2023

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models NIPS 2023

Architectural Backdoors in Neural Networks CVPR 2023

EffCRN: An Efficient Convolutional Recurrent Network for High-Performance Speech Enhancement INTERSPEECH 2023

HyperMixer: An MLP-based Low Cost Alternative to Transformers ACL 2023