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
Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment
Offline Reinforcement Learning with Generative Trajectory Policies
Offline Reinforcement Learning with Universal Horizon Models
Offline Two-Player Zero-Sum Markov Games with KL Regularization
Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random
Off-Policy Evaluation with Strategic Agents via Local Disclosure
Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
Olaf-World: Orienting Latent Actions for Video World Modeling
Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\ell_\infty$ Implicit Biases
OLion: Approaching the Hadamard Ideal by Intersecting Spectral and L inf Implicit Biases
Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density
Olmix: A Framework for Data Mixing Throughout LM Development
OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
Omitted Variable Bias in Language Models Under Distribution Shift
OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild
OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
OmniFit: Bridging Modalities via Layer-Adaptive Token Compression for Omnimodal Large Language Models
Omni-fMRI: A Universal Atlas-Free fMRI Foundation Model
OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale
Omni-Perception Policy Optimization for Multimodal Emotion Reasoning
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention
OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL
OMP: One-step Meanflow Policy with Directional Alignment
Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation
On Contraction of Sequential and Offset Rademacher Complexities
On Densest $k$-Subgraph Mining and Diagonal Loading: Optimization Landscape and Finite-Step Exact Convergence Analysis
One Batch Is Enough: A Unified Dataset Condensation Framework for General Time Series Analysis
One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discovery
One Coin Has Two Sides: Single Poistive Multi Label Learning from Salient Annotations
One Coin Has Two Sides: Single Positive Multi Label Learning from Salient Annotations
On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
On Efficient Scaling of GNNs via IO-Aware Layers Implementations
One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State
One LR Doesn’t Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception
OnePO: Direct One-stage Policy Optimization for SFT-free Domain Adaptation
One Probe Won’t Catch Them All: Towards Targeted Deception Detection
OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search
One-shot Conditional Sampling: MMD meets Nearest Neighbors
One-shot Entropy Minimization for Language Model Reasoning
One-Shot Weighted Ensemble Estimation for Federated Quantile Regression: Optimal Statistical Guarantees under Heterogeneous Structured Data
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

« prev Page 78/130 next »