ICML 2024
2,660 papers
Top Research Directions
Research directions most represented by ICML 2024 papers.
Top Authors
Impactful Papers
Papers from ICML 2024 that shaped research clusters.
Foundational
On the Independence Assumption in Neurosymbolic Learning
foundational
Overcoming the Independence Assumption i
Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks
foundational
Emergent Alignment Dynamics from Regular
Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection
foundational
Budget-Aware Data Selection Strategies
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
foundational
The Imitation Trap in Weak-to-Strong Gen
Position: Graph Foundation Models Are Already Here
foundational
Natural Language as a Universal Feature
Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge
foundational
Unifying Diffusion and Flow Matching via
Towards Efficient Exact Optimization of Language Model Alignment
foundational
Mode Seeking Objectives for Alignment an
ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback
foundational
Multi-Dimensional Reward Decomposition f
PID: Prompt-Independent Data Protection Against Latent Diffusion Models
foundational
Adversarial Perturbations at the Encoder
Influential
Linguistic Calibration of Long-Form Generations
influential
Aligning Model Confidence via Proper Sco
3D Geometric Shape Assembly via Efficient Point Cloud Matching
influential
Hierarchical Coarse to Fine Corresponden
Model Alignment as Prospect Theoretic Optimization
influential
Unpaired Preference Optimization with Bi
Pi-DUAL: Using privileged information to distinguish clean from noisy labels
influential
Low-Rank Decomposition for Robust Label
Disentangled 3D Scene Generation with Layout Learning
influential
Layered and Part-Based 3D Representation
Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration
influential
Preventing Entropy Collapse in Reinforce
QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference
influential
The Memory Bandwidth Bottleneck in Trans
Model Assessment and Selection under Temporal Distribution Shift
influential
Adaptive Temporal Windows for Non-Statio
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Bia
influential
The Identifiability Problem in Reward Le