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
On the Expressive Power of Permutation-Equivariant Weight-Space Networks
On the Fragility of Data Attribution When Learning Is Distributed
On the Generalization Gap in Self-Evolving Language Model Reasoning
On the Generalization in Topology Optimization via Sensitivity-Conditioned Bernoulli Flow Matching
On the Identifiability of Poisson Branching Structural Causal Model Under Latent Confounding
On the "Induction Bias" in Sequence Models
On the Infinite Width and Depth Limits of Predictive Coding Networks
On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
On the Intrinsic Limits of Transformer Image Embeddings in Non-Solvable Spatial Reasoning
On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference
On the Optimization Trajectory of DeepWalk Embeddings
On the Origin of Neural Scaling Laws: from Random Graphs to Natural Language
On the Plasticity and Stability for Post-Training Large Language Models
On the Power of (Approximate) Reward Models for Inference-Time Scaling: Sequential Monte Carlo and Beyond
On the Power of Source Screening for Learning Shared Feature Extractors
On the Power of Statistics in Class-Incremental Learning with Pretrained Models
On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
On the Robustness of Langevin Dynamics to Score Function Error
On the Role of Batch Size in Stochastic Conditional Gradient Methods
On the Role of Computation in Reinforcement Learning
On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective
On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
On the Separability of Information in Diffusion Models
On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks
On the Spectral Unreachability of Brain Graph Learning
On the Theoretical Limitations of Embedding-based Link Prediction
On the Theory of Continual Learning with Gradient Descent for Neural Networks
On the Variability of Concept Activation Vectors
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise
OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection
Op-CAD: Benchmarking and Investigating Operation-oriented CAD Generation
OpenDeception: Learning Deception and Trust in Human–AI Interaction via Multi-Agent Simulation
OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph
Open Materials Generation with Inference-Time Reinforcement Learning
Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
OpenSage: Self-programming Agent Generation Engine
Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection
OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
Open-World LLM Logical Reasoning
Operationalising the Superficial Alignment Hypothesis via Task Complexity
Operator Splitting with Hamilton-Jacobi-based Proximals
Ophiuchus: Incentivizing Tool-augmented ''Think with Images'' for Joint Medical Segmentation, Understanding and Reasoning
OPIC: Enhancing Language Model Merging via Optimizing In-Context Capability

« prev Page 80/130 next »