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
Multiview Self-Representation Learning across Heterogeneous Views
MultiVulnBench: A Large-Scale Benchmark for Count Bias in LLM-Based Multi-Vulnerability Detection
Multi-Way Representation Alignment
Muon in Associative Memory Learning: Training Dynamics and Scaling Laws
MuonSSM: Orthogonalizing State Space Models for Sequence Modeling
MUSA-PINN: Multi-scale Weak-form Physics-Informed Neural Networks for Fluid Flow in Complex Geometries
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
MusicDET: Zero-Shot AI-Generated Music Detection
Must All Negatives Be Pushed Away Equally? Uncertainty-Aware Cross-View Geo-Localization via Normal Inverse Gamma Distribution
MutAtlas: A PDB-Wide Energy-Guided Atlas of Protein Mutation Effects
MV-FGAD: Towards Efficient and Effective Federated Graph Anomaly Detection via Multi-view Learning
MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs
MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation
MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction
MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation
N2M: Bridging Navigation and Manipulation by Learning Pose Preference from Rollout
NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating
Names Don’t Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning
NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices
NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
NanoSpec: Accelerating Speculative Decoding using Minimalist In-Context Vocabularies
NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs
Narrowing the ANN–SNN Gap for Continuous 1D Temporal Signal Classification with Multi-Scale Temporal Encoding and Sparsity-Regularized Transform Encoding
Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation
Native Active Perception as Reasoning for Omni-Modal Understanding
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
Native Spatio-Temporal 4D Variational Autoencoder
Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
NaviAgent: Graph‑Driven Bilevel Planning for Scalable Tool Orchestration
NaviCache: Test-Time Self-Calibration Caching for Video Generation
NAVIGATE: Evaluating Visual-Guided Search Decision-Making on the Open Web
Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
Navigating the Energy Landscape of Collaboration: Multi-Agent Communication Graph Generation via Score-Based Diffusion
Navigating the Flatlands: Dual Adaptive Sharpness-Aware Minimization for Domain Generalization
Navigating the Pareto Frontier of Alignment: Spectrum-Adaptive Fine-Tuning for LLMs
NavOL: Navigation Policy with Online Imitation Learning
NBCG: Nash-Bargained Causal Game for Long-Tailed Multi-Label NLP
nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding
Near-Minimax Multi-Objective RL under Predictable Adversarial Preferences and Preference-Free Exploration in Linear MDPs
Near-Optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation
Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0,L_1)$-Smoothness
Near-Optimal Dynamic Matching via Coarsening with Application to Heart Transplantation
Near-Optimal Private Linear Regression via Iterative Hessian Mixing
Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation
Near-Universal Multiplicative Updates for Nonnegative Einsum Factorization
Needles in the Haystack: Addressing Signal Dilution Improves scRNA-seq Perturbation Response Modeling and Evaluation
Negative Sampling From the Ground Up: A Redesign for Recommendation
Negative Sampling From the Ground Up: A Redesign for Recommendations
Negatives-Dominant Contrastive Learning for Generalization in Imbalanced Domains

« prev Page 75/130 next »