ICML 2024

2,660 papers

Top Research Directions

Research directions most represented by ICML 2024 papers.

Overcoming the Iterative Inference Latency of Diffusion Models 24
Safe Reinforcement Learning via Constrained Markov Decision Processes 21
The Non-Linear Function Approximation Gap in Reinforcement Learning 21
Sample Efficient Reinforcement Learning 21
Clean Accuracy Degradation in Machine Learning Defenses 21
Overcoming the Homophily Assumption in Graph Neural Networks 18
The Mechanics of Backdoor Attacks in Neural Networks 17
The Weisfeiler Lehman Expressivity Bottleneck 16
The Function Approximation Gap in Reinforcement Learning Theory 16
Mitigating Gradient Variance in Policy Optimization 14
Matrix-Free Curvature Estimation for Deep Learning 14
Optimization and Generalization with Non-Smooth Activations 14
Accelerating Sparse Neural Networks on Dense Hardware 14
Scaling Gaussian Processes Beyond Cubic Complexity 14
Bypassing the Computational Bottleneck of Adversarial Training 14

Top Authors

AuthorPapers
Bo Li12
James Y. Zou12
Jianye HAO12
Pin-Yu Chen11
Tongliang Liu11
James Zou10
Junchi Yan10
Sergey Levine10
Stan Z. Li10
Volkan Cevher10
Zhangyang Wang10
Dacheng Tao9
Furong Huang9
Rongrong Ji9
Taiji Suzuki9
Andrew Gordon Wilson8
Bo Han8
David Woodruff8
Dawn Song8
De-Chuan Zhan8

Impactful Papers

Papers from ICML 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
Position: Social Environment Design Should be Further Developed for AI-based Policy-Making
Position: Standardization of Behavioral Use Clauses is Necessary for the Adoption of Responsible Licensing of AI
Position: Stop Making Unscientific AGI Performance Claims
Position: Technical Research and Talent is Needed for Effective AI Governance
Position: Tensor Networks are a Valuable Asset for Green AI
Position: The Causal Revolution Needs Scientific Pragmatism
Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
Position: The Platonic Representation Hypothesis
Position: The Reasonable Person Standard for AI
Position: Topological Deep Learning is the New Frontier for Relational Learning
Position: Towards Implicit Prompt For Text-To-Image Models
Position: Towards Unified Alignment Between Agents, Humans, and Environment
Position: TrustLLM: Trustworthiness in Large Language Models
Position: Understanding LLMs Requires More Than Statistical Generalization
Position: Video as the New Language for Real-World Decision Making
Position: What Can Large Language Models Tell Us about Time Series Analysis
Position: What makes an image realistic?
Position: Why Tabular Foundation Models Should Be a Research Priority
Position: Why We Must Rethink Empirical Research in Machine Learning
Position: Will we run out of data? Limits of LLM scaling based on human-generated data
Positive and Unlabeled Learning with Controlled Probability Boundary Fence
Positive Concave Deep Equilibrium Models
Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds
Post-hoc Part-Prototype Networks
Potential Based Diffusion Motion Planning
PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching
Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity Theory
Practical Performance Guarantees for Pipelined DNN Inference
Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms
Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
Predicting Dose-Response Curves with Deep Neural Networks
Predicting Lagrangian Multipliers for Mixed Integer Linear Programs
Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg
Prediction-powered Generalization of Causal Inferences
Predictive Coding beyond Correlations
Predictive Dynamic Fusion
Predictive Linear Online Tracking for Unknown Targets
Predictive Performance Comparison of Decision Policies Under Confounding
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
Premise Order Matters in Reasoning with Large Language Models
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
Pre-Training Protein Bi-level Representation Through Span Mask Strategy On 3D Protein Chains
Preventing Model Collapse in Gaussian Process Latent Variable Models
Pricing with Contextual Elasticity and Heteroscedastic Valuation
Principal Component Flows
Principled Gradient-Based MCMC for Conditional Sampling of Text

« prev Page 38/54 next »