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
Improved Bounds for Private and Robust Alignment
Improved Bounds for Reward-Agnostic and Reward-Free Exploration
Improved Convergence Analysis of Topology Dependence in Decentralized SGD
Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variation
Improved Distribution Estimation in $\ell_\infty$
Improved Dynamic Algorithm for Non-monotone Submodular Maximization under Cardinality Constraint
Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression
Improved Scaling Laws via Weak-to-Strong Generalization in Random Features Ridge Regression
Improved Stochastic Optimization of LogSumExp
Improving Adversarial Robustness of Attribution via Implicit Regularization
Improving Backward Conformal Prediction via Non-Conformity Score Transformation
Improving Classifier-Free Guidance of Flow Matching via Manifold Projection
Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
Improving Diffusion Planners by Self-Supervised Action Gating with Energies
Improving Explicit Dynamic Gaussian Splatting Optimization via Update Mixture
Improving LLM-Based Recommenders with Conservative Generative Flow Networks
Improving ML Attacks on LWE with Data Repetition and Stepwise Regression
Improving Sampling for Masked Diffusion Models via Information Gain
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
Improving the Robustness-Utility Trade-off in Decentralized Learning over Sparse Networks
Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
Improving Topic Modeling by Distilling Soft Labels from Language Models
Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference
Improving Zero-Shot Offline RL via Behavioral Task Sampling
ImpText: A Benchmark and Tool-Augmented Framework for Implicit Text Reasoning
Incentivized Exploration with Stochastic Covariates: A Two-Stage Mechanism Design for Recommender System
Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning
Incomplete Multi-View Clustering via Neighborhood-Conditioned Diffusion
Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data
In-Context Generation with Regional Constraints for Instructional Video Editing
In-Context Learning as Rate–Distortion Optimization
In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
In-Context Universal Approximation, Compositional Generalization, and Algorithm Emulation
Incorporating Importance Weighting in Optimal Transport Based Domain Alignment
Incremental BPE Tokenization
Incremental Learning of Sparse Attention Patterns in Transformers
Incremental Transformer Neural Processes
Independent Component Discovery in Temporal Count Data
INDEXGUARD: Index-only Backdoor Vetting for Secure Federated PEFT of Large Language Models
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference
Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
INDUCTION: Finite-Structure Concept Synthesis in First-Order Logic
Induction Heads Interpolate N-Grams
Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models
InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames
Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO
Inference from Quantized Data via Normal Variance-Mean Mixtures
Inference of Online Newton Methods with Nesterov's Accelerated Sketching
Inference-time Alignment with Rewards in Besov Spaces: Provable Advantages of Feature Learning and Multi-Step Policy Updates
Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models

« prev Page 56/130 next »