conftrace_
← Techniques
Deep Learning › Techniques ›

Model Architecture

4,351 papers

Papers per year

1
22
405
505
'10
'15
'20
'25

Papers

Discrete Key-Value Bottleneck ICML 2023
Mimetic Initialization of Self-Attention Layers ICML 2023
Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single ICML 2023
UPSCALE: Unconstrained Channel Pruning ICML 2023
DIVISION: Memory Efficient Training via Dual Activation Precision ICML 2023
Direct Parameterization of Lipschitz-Bounded Deep Networks ICML 2023
Discover and Cure: Concept-aware Mitigation of Spurious Correlation ICML 2023
Bit Allocation using Optimization ICML 2023
SLAMB: Accelerated Large Batch Training with Sparse Communication ICML 2023
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks ICML 2023
Adaptive Computation with Elastic Input Sequence ICML 2023
Distortion and Uncertainty Aware Loss for Panoramic Depth Completion ICML 2023
Improving Visual Prompt Tuning for Self-supervised Vision Transformers ICML 2023
COLA: Orchestrating Error Coding and Learning for Robust Neural Network Inference Against Hardware Defects ICML 2023
LookupFFN: Making Transformers Compute-lite for CPU inference ICML 2023
Bi-directional Masks for Efficient N:M Sparse Training ICML 2023
Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration ICML 2023
Brainformers: Trading Simplicity for Efficiency ICML 2023
SlotGAT: Slot-based Message Passing for Heterogeneous Graphs ICML 2023
Phase-aware Adversarial Defense for Improving Adversarial Robustness ICML 2023
GeNAS: Neural Architecture Search with Better Generalization IJCAI 2023
SWAT: Spatial Structure Within and Among Tokens IJCAI 2023
Divide Rows and Conquer Cells: Towards Structure Recognition for Large Tables IJCAI 2023
Accurate MRI Reconstruction via Multi-Domain Recurrent Networks IJCAI 2023
Efficient Multi-View Inverse Rendering Using a Hybrid Differentiable Rendering Method IJCAI 2023