ICLR 2023

3,358 papers

Top Research Directions

Research directions most represented by ICLR 2023 papers.

Clean Accuracy Degradation in Machine Learning Defenses 22
Over-Smoothing in Graph Neural Networks 21
Bypassing the Computational Bottleneck of Adversarial Training 21
The Non-Linear Function Approximation Gap in Reinforcement Learning 15
Sample Efficient Reinforcement Learning 15
The Weisfeiler Lehman Expressivity Bottleneck 12
Overcoming the Homophily Assumption in Graph Neural Networks 12
Accelerating Neural Architecture Search Without Full Model Training 12
The Sensitivity of Multi-Objective Loss Balancing 12
Unifying Self-Supervised Learning via Spectral and Information Theory 11
Out of Distribution Overestimation in Offline Reinforcement Learning 11
Distribution Shift in Offline Reinforcement Learning 11
The Mechanics of Backdoor Attacks in Neural Networks 11
Geometric Equivariance in 3D Molecular Deep Learning 10
Optimization and Generalization with Non-Smooth Activations 10

Top Authors

AuthorPapers
Tongliang Liu22
Junchi Yan21
Dacheng Tao19
Zhangyang Wang19
Bo Han18
Shuicheng YAN17
Sergey Levine16
Micah Goldblum15
Joshua B. Tenenbaum14
Sung Ju Hwang14
Jianye HAO13
Kun Zhang13
Tom Goldstein13
Jakob Nicolaus Foerster12
Yann LeCun12
Andrew Gordon Wilson11
Dale Schuurmans11
Pieter Abbeel11
Yoshua Bengio11
Chelsea Finn10

Impactful Papers

Papers from ICLR 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
A Theory of Equivalence-Preserving Program Embeddings
A theory of representation learning in neural networks gives a deep generalisation of kernel methods
A Time-Consistency Curriculum for Learning from Instance-Dependent Noisy Labels
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
Atomized Deep Learning Models
Attention De-sparsification Matters: Inducing Diversity in Digital Pathology Representation Learning
Attention Enables Zero Approximation Error
Attention Flows for General Transformers
Attention-Guided Backdoor Attacks against Transformers
AudioGen: Textually Guided Audio Generation
Auditing Fairness Online through Interactive Refinement
Augmentation Backdoors
Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlaps
Augmentation Curriculum Learning For Generalization in RL
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
Augmentative Topology Agents For Open-Ended Learning
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
A Unified Causal View of Domain Invariant Representation Learning
A Unified Framework for Comparing Learning Algorithms
A Unified Framework for Soft Threshold Pruning
A unified optimization framework of ANN-SNN Conversion: towards optimal mapping from activation values to firing rates
A UNIFIED VIEW OF FINDING AND TRANSFORMING WINNING LOTTERY TICKETS
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
Auto-Encoding Adversarial Imitation Learning
Auto-Encoding Goodness of Fit
Autoencoding Hyperbolic Representation for Adversarial Generation
AutoGT: Automated Graph Transformer Architecture Search
AUTOJOIN: EFFICIENT ADVERSARIAL TRAINING FOR ROBUST MANEUVERING VIA DENOISING AUTOEN- CODER AND JOINT LEARNING
Automated Data Augmentations for Graph Classification
Automatically Answering and Generating Machine Learning Final Exams
Automatically Auditing Large Language Models via Discrete Optimization
Automatic Chain of Thought Prompting in Large Language Models
Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
AUTOMATIC CURRICULUM FOR UNSUPERVISED REIN- FORCEMENT LEARNING
Automatic Curriculum Generation for Reinforcement Learning in Zero-Sum Games
Automating Nearest Neighbor Search Configuration with Constrained Optimization
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Autoregressive Conditional Neural Processes
Autoregressive Generative Modeling with Noise Conditional Maximum Likelihood Estimation
AutoSKDBERT: Learn to Stochastically Distill BERT
AutoTransfer: AutoML with Knowledge Transfer - An Application to Graph Neural Networks
Auxiliary task discovery through generate and test
A VAE for Transformers with Nonparametric Variational Information Bottleneck
Average Sensitivity of Decision Tree Learning
A View From Somewhere: Human-Centric Face Representations
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.
Avoiding spurious correlations via logit correction
Axiomatic Explainer Locality With Optimal Transport
Backdoor Mitigation by Correcting Activation Distribution Alteration
Backdoor or Feature? A New Perspective on Data Poisoning

« prev Page 6/68 next »