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
Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution
Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization
Origo: Interpretable Multi-physics PDE Foundation Model through Neural Operator Splitting
ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research
Orthogonal Concept Erasure for Diffusion Models
Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models
Orthogonal Model Merging
OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
OSCS: Online Selection with Provable FAR Control for LLM Safety
OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration
OSF: On Pre-training and Scaling of Sleep Foundation Models
OSM+: Billion-Level Open Street Map Dataset for City-wide Experiments
OSNIP: Balancing the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
Out-of-Distribution Evaluation of Rule-Based and Strategic Reasoning in Chess Transformers
Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All
Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization
Overclocking Electrostatic Generative Models
Overcoming PINNs Failure Modes In High Dimension With Low-Rank Fourier Sum
Overcoming the Incentive Collapse Paradox
Overcoming the Modality Gap in Context-Aided Forecasting
Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
OvisOCR: End-to-End Document Parsing via Aligning Specialized Perception with General Reasoning
OVLR: Efficient, Scalable, and Robust Training via Output-Level Variance-Reduced Likelihood Ratio
OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
PACEAttention: Principled and Adaptive Feature Compression-Expansion Grounded in the Geometry of $\text{MCR}^2$
PACE: Parameter Change for Unsupervised Environment Design
PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression
PACER: Acyclic Causal Discovery from Large-scale Interventional Data
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
PADA-Coder: Improving Plan-Following Code Generation via Perturbation-Verified Attention Distillation and Dynamic Alignment
PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning
PADS-TAL: Padding-Annealed Diffusion Sampling in Text-Aware Latent Space for Robust and Diverse Text-to-Music Generation
Pair2Scene: Learning Local Object Relations for Procedural Scene Generation
PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning
Panini: Continual Learning in Token Space via Structured Memory
PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion
PaperBanana: Automating Academic Illustration for AI Scientists
ParalESN: Enabling parallel information processing in Reservoir Computing
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
Parallel Stochastic Gradient-Based Planning for World Models
Parameter Decorrelation via Transition-Variance Alignment for Multivariate Time-series Forecasting
Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory
Parameter Manifold Purification
Parameter-Masked Decoupled Optimization for Cross-Domain Class-Incremental Learning
Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting

« prev Page 82/130 next »