ICML 2026

6,487 papers

Top Research Directions

Research directions most represented by ICML 2026 papers.

Scaling Language Model Reasoning Beyond Verifiable Rewards 79
Group Relative Policy Optimization for Large Reasoning Models 63
General Purpose Reasoning from Specialized Reinforcement Learning 62
Overcoming the Iterative Inference Latency of Diffusion Models 50
Shifting from Static Benchmarks to Dynamic Evaluation 47
Controlling Language Models Through Latent Space Interventions 45
Resolving Superposition with Sparse Autoencoders 42
Autonomous Code Refinement via Execution Feedback Loops 41
The Performance Cliff in Ultra Low Bit Quantization 41
Activation Steering for Inference Time Model Control 39
Mitigating Expert Collapse in Sparse Mixture of Experts 37
Proxy Objective Exploitation in Language Model Alignment 37
The Decoupling of Visual Perception and Logical Reasoning 36
Mitigating Computational Overthinking in Large Reasoning Models 35
Input Adaptive Compute Allocation for Language Models 33

Top Authors

AuthorPapers
Junchi Yan19
Min Zhang19
Tat-Seng Chua15
Haoxuan Li14
Philip Torr14
Yong Li14
Kun Zhang13
Li Shen13
Tianlong Chen13
Xiang Wang13
Xin Geng13
Yejin Choi13
Bo An12
Mihaela van der Schaar12
Xunliang Cai12
Bo Han11
Ge Zhang11
Han Liu11
Jiang Bian11
LEI BAI11

Impactful Papers

Papers from ICML 2026 that shaped research clusters.

Foundational

Papers

Title
Personalized Policy Learning through Discrete Experimentation
Persona-Pruner: Sculpting Lightweight Models for Role-Playing
Persuasive Privacy
PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling
PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting
Pessimistic Verification for Open-Ended Math Questions
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials
PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection
PGD-NO: A Neural Operator with Precomputed Geometry Decomposition for 3D Million-Scale Physics Simulations
PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
PHALAR: Phasors for Learned Musical Audio Representations
PhaseAlign: Complex Phase Alignment for Stable Open-Vocabulary Semantic Segmentation
Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs
Phase-Type Variational Autoencoders for Heavy-Tailed Data
PhenoBrain: Phenotype-Conditioned Long-Range Communication for Multi-Modal Brain Network Analysis
PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios
PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models
Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Spectral Super-Resolution for Snapshot Compressive Imaging
PhyScene3D: Physically Consistent 3D Interactive Tabletop Scene Generation
PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation
PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions
Physically-Guided Data-Space Rectified Flow for Precipitation Nowcasting
Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions
Physics-Guided Motion Loss for Video Generation Model
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Physics-informed coarsening for multigrid graph neural networks surrogates
Physics-Informed Coarsening for Multigrid Graph Neural Surrogates
Physics-Informed Diffusion Models in Spectral Space
Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generation
Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov Equation
Physics-Informed Pre-training on Efficient Electron-Density Images for Organic Material Property Prediction
Physics-Informed Residual Flows
Physiology as Language: Translating Respiration to EEG during Sleep
Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning
Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization
PINE: Pruning Boosted Tree Ensembles with Conformal In-Distribution Prediction Equivalence
PINNfluence: Interpreting PINNs through Influence Functions
PinTok: Tokenizers Deserve Dedicated Pinned CPU-Compute and Memory
PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
PISA: Privacy-Preserving Split Adaptation with Model IP Protection
PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards
Pix2Key: Controllable Open-Vocabulary Retrieval with Semantic Decomposition and Self-Supervised Visual Dictionary Learning
PixCLIP: Towards Fine-grained Vision-Language Understanding via Any-granularity Pixel-Text Alignment
PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design
Plain Transformers are Surprisingly Powerful Link Predictors

« prev Page 84/130 next »