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
Unified Training of Universal Time Series Forecasting Transformers
Uniformly Stable Algorithms for Adversarial Training and Beyond
Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations
Unifying Image Processing as Visual Prompting Question Answering
Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
Universal Gradient Methods for Stochastic Convex Optimization
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training
Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation
Unmasking Vulnerabilities: Cardinality Sketches under Adaptive Inputs
Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
Unsupervised Concept Discovery Mitigates Spurious Correlations
Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images
Unsupervised Episode Generation for Graph Meta-learning
Unsupervised Evaluation of Code LLMs with Round-Trip Correctness
Unsupervised Parameter-free Simplicial Representation Learning with Scattering Transforms
Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional Connectivity
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
Unveiling Privacy, Memorization, and Input Curvature Links
Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression
Unveiling the Dynamics of Information Interplay in Supervised Learning
Unveiling the Potential of AI for Nanomaterial Morphology Prediction
UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis
UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers
UPOCR: Towards Unified Pixel-Level OCR Interface
Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers
Using AI Uncertainty Quantification to Improve Human Decision-Making
Using Left and Right Brains Together: Towards Vision and Language Planning
Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs
USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval
Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection
Value-Evolutionary-Based Reinforcement Learning
Vanilla Bayesian Optimization Performs Great in High Dimensions
Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
Variational Inference with Coverage Guarantees in Simulation-Based Inference
Variational Learning is Effective for Large Deep Networks
Variational Linearized Laplace Approximation for Bayesian Deep Learning
Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts
Variational Schrödinger Diffusion Models
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention
Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations
Vector Quantization Pretraining for EEG Time Series with Random Projection and Phase Alignment
Verification of Machine Unlearning is Fragile
Verifying message-passing neural networks via topology-based bounds tightening
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
VideoPoet: A Large Language Model for Zero-Shot Video Generation

« prev Page 52/54 next »