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
Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling
OptiFluence: Principled Design of Privacy Canaries
Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints
Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy
Optimal Decision-Making Based on Prediction Sets
Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification
Optimal Domain-Aware Privacy Mechanisms for Synthetic Data Generation
Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints
Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech
Optimal Learning from Label Proportions with General Loss Functions
Optimal Pricing for Data-Augmented AutoML Marketplaces
Optimal Quantum Speedups for Repeatedly Nested Expectation Estimation
Optimal Rates for Feasible Payoff Set Estimation in Games
Optimal Regret for Policy Optimization in Contextual Bandits
Optimal Regularization for Performative Learning
Optimal Self-Consistency for Efficient Reasoning with Large Language Models
Optimal Splitting of Language Models from Mixtures to Specialized Domains
Optimal Stopping in Latent Diffusion Models
Optimal structure learning and conditional independence testing
Optimal Top-$k$ Identification from Pairwise Comparisons
Optimal Transport for LLM Reward Modeling from Noisy Feedback
Optimal Transport Group Counterfactual Explanations
Optimal Transport–Guided Stochastic Control for Graph Combinatorial Optimization
Optimal Transport under Group Fairness Constraints
Optimal Transport with Symmetry Groups
Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning
Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold Networks
Optimized Deferral for Imbalanced Settings
Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
Optimizing Diversity and Quality through Base-Aligned Model Collaboration
Optimizing Few-Step Generation with Adaptive Matching Distillation
Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification
Optimizing Network Simulation: Enhancing Performance Prediction Accuracy via Neural Architecture Search
Optimizing Rank for High-Fidelity Implicit Neural Representations
Optimizing Visual Generative Models via Distribution-wise Rewards
OPTION: Optimal Transport–Guided Flow Matching for Incomplete and Unaligned Multi-View Clustering
OptMaster: A DAG-Based Framework for Formulation and Heuristic Discovery in Optimization
Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization Modeling
OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
ORBIT: A Prognostic World Model for Ocular Reasoning Based on Imagined Trajectories
Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation
OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
Ordered Stick-Breaking Prior for Sequential MCMC Inference of Bayesian Nonparametric Models
Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching

« prev Page 81/130 next »