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
Noise as a Natural Regularizer in Markov Decision Processes: Connecting Environmental Stochasticity and Policy Simplicity
Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
Noise-Guided Transport: Imitation Learning from Random Priors
Noise-Robust Density Estimation for Tabular Data Anomaly Detection
NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervision
Noisy-Channel Minimum Bayes Risk Decoding
Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization
Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning
NOMAD: Lifelong Trajectory Planning via Non-Parametric Bayesian Memory-Adaptive Diffusion Experts
No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
No More, No Less: Least-Privilege Language Models
Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism
Nonconvex Low-Rank Tensor Representation with Deep Priors for Multiview Subspace Clustering
No Need to Train Your RDB Foundation Model
Non-Euclidean Gradient Descent Operates at the Edge of Stability
Nonlinear Covariate Balance in Experimental Design
Non-Monotonic Autoregressive Sequence Model
Nonparametric Data Attribution for Diffusion Models
Nonparametric Distribution Regression Re-calibration
Nonparametric LLM Evaluation from Preference Data
Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems
Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
Non-Parametric Structural Priors for Geometry Theorem Prediction
Non-Stationary Online Structured Prediction with Surrogate Losses
Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator
NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
No Retraining at Edge: Efficient Resource-Aware Mixed-Precision Quantization via Federated Supernet Learning
Norm$\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention
Normality Calibration in Semi-supervised Graph Anomaly Detection
Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising
Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
Normalized Rewards for Preference Optimization
Normalizing Flows with Iterative Denoising
NorMuon: Making Muon more efficient and scalable
Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence
Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series Forecasting
Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving
Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
Object-level Semantic and Spatial Distillation for Open Vocabulary Detection
ObjEmbed: Towards Universal Multimodal Object Embeddings
OBJVanish: Prompt-Driven Generation of Physically Realizable 3D LiDAR-Invisible Objects
Obliviate: Efficient Unlearning in Recommender Systems
OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation
OCNR: Stabilizing Self-Play by Mitigating Iteration-Collapse With One-Class Novelty Rewards
OC-space: a Unifying Perspective on Verification of Tree Ensembles
Offline Multi-agent Continual Cooperation via Skill Partition and Reuse
Offline Multi-Agent Reinforcement Learning via Sequential Score Decomposition
Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs

« prev Page 77/130 next »