ICLR 2022

2,337 papers

Top Research Directions

Research directions most represented by ICLR 2022 papers.

Bypassing the Computational Bottleneck of Adversarial Training 21
Sample Efficient Reinforcement Learning 19
The Mechanics of Benign Overfitting in High Dimensions 18
Clean Accuracy Degradation in Machine Learning Defenses 17
Overcoming the Homophily Assumption in Graph Neural Networks 13
Accelerating Sparse Neural Networks on Dense Hardware 13
Accelerating Neural Architecture Search Without Full Model Training 12
The Non-Linear Function Approximation Gap in Reinforcement Learning 12
The Mechanics of Backdoor Attacks in Neural Networks 12
Beyond the Lazy Training Regime of Neural Networks 11
The Infinite Width Approximation Gap in Deep Learning 10
Matrix-Free Curvature Estimation for Deep Learning 10
The Computational Overhead of Iterative Model Pruning 9
The Weisfeiler Lehman Expressivity Bottleneck 9
Why Theoretical FLOPs Fail to Predict Real Latency 9

Top Authors

AuthorPapers
Zhangyang Wang23
Sergey Levine21
Tianlong Chen15
Tongliang Liu14
Bo Han13
Chelsea Finn13
Gang Niu13
Jun Wang13
Yoshua Bengio13
Bernhard Schölkopf12
Joshua B. Tenenbaum12
J Zico Kolter12
Ping Li12
Tie-Yan Liu12
Dacheng Tao11
Stephan Günnemann11
Tom Goldstein11
Masashi Sugiyama10
Pieter Abbeel9
Pin-Yu Chen9

Impactful Papers

Papers from ICLR 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Variability of Neural Networks and Han-Layer: A Variability-Inspired Model
Variance Reduced Domain Randomization for Policy Gradient
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias
Variational Component Decoder for Source Extraction from Nonlinear Mixture
Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion
Variational Inference via Resolution of Singularities
Variational methods for simulation-based inference
Variational Neural Cellular Automata
Variational oracle guiding for reinforcement learning
Variational Predictive Routing with Nested Subjective Timescales
VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects
VC dimension of partially quantized neural networks in the overparametrized regime
Vector-quantized Image Modeling with Improved VQGAN
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
Video Forgery Detection Using Multiple Cues on Fusion of EfficientNet and Swin Transformer
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
VISCOS Flows: Variational Schur Conditional Sampling with Normalizing Flows
Vision-Based Manipulators Need to Also See from Their Hands
Visual Correspondence Hallucination
Visual hyperacuity with moving sensor and recurrent neural computations
Visually-augmented pretrained language models for NLP Tasks without Images
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Visual Representation Learning over Latent Domains
ViTGAN: Training GANs with Vision Transformers
Vitruvion: A Generative Model of Parametric CAD Sketches
VoiceFixer: Toward General Speech Restoration with Neural Vocoder
VOS: Learning What You Don't Know by Virtual Outlier Synthesis
VUT: Versatile UI Transformer for Multimodal Multi-Task User Interface Modeling
Wakening Past Concepts without Past Data: Class-incremental Learning from Placebos
Wavelet Feature Maps Compression for Low Bandwidth Convolutional Neural Networks
Wavelet-Packet Powered Deepfake Image Detection
W-CTC: a Connectionist Temporal Classification Loss with Wild Cards
Weakly Supervised Graph Clustering
Weakly-Supervised Learning of Disentangled and Interpretable Skills for Hierarchical Reinforcement Learning
WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection
Weighted Training for Cross-Task Learning
What can multi-cloud configuration learn from AutoML?
What classifiers know what they don't know?
What does a platypus look like? Generating customized prompts for zero-shot image classification
What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning
What Do We Mean by Generalization in Federated Learning?
What Happens after SGD Reaches Zero Loss? --A Mathematical Framework
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different
What's Behind the Mask: Estimating Uncertainty in Image-to-Image Problems
What's Wrong with Deep Learning in Tree Search for Combinatorial Optimization
WHAT TO DO IF SPARSE REPRESENTATION LEARNING FAILS UNEXPECTEDLY?
What Would the Expert $do(\cdot)$?: Causal Imitation Learning
When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?
When Complexity Is Good: Do We Need Recurrent Deep Learning For Time Series Outlier Detection?

« prev Page 46/47 next »