conftrace_
← Techniques
Deep Learning › Techniques ›

Model Architecture

4,354 papers

Papers per year

1
22
405
506
'10
'15
'20
'25

Papers

FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization ICML 2023
Minimizing Trajectory Curvature of ODE-based Generative Models ICML 2023
TIPS: Topologically Important Path Sampling for Anytime Neural Networks ICML 2023
Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning ICML 2023
Cones: Concept Neurons in Diffusion Models for Customized Generation ICML 2023
Reflected Diffusion Models ICML 2023
Mechanistic Mode Connectivity ICML 2023
Pruning via Sparsity-indexed ODE: a Continuous Sparsity Viewpoint ICML 2023
Input uncertainty propagation through trained neural networks ICML 2023
Achieving High Accuracy with PINNs via Energy Natural Gradient Descent ICML 2023
Equivariant Architectures for Learning in Deep Weight Spaces ICML 2023
Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach ICML 2023
SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge ICML 2023
Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction ICML 2023
How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy ICML 2023
Resurrecting Recurrent Neural Networks for Long Sequences ICML 2023
Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs ICML 2023
Brauer’s Group Equivariant Neural Networks ICML 2023
How Jellyfish Characterise Alternating Group Equivariant Neural Networks ICML 2023
Hyena Hierarchy: Towards Larger Convolutional Language Models ICML 2023
Beam Tree Recursive Cells ICML 2023
Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit ICML 2023
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient ICML 2023
The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023
All in a Row: Compressed Convolution Networks for Graphs ICML 2023