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
Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models
Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
SOLAR for Offline MARL: Plateau-Triggered Potential Shaping under World-Model Uncertainty
SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval
Solving Imperfect-Recall Games via Sum-of-Squares Optimization
Solving Inverse Problems with Flow-based Models via Model Predictive Control
Solving Positive Linear Programs with Differential Privacy
Solving Spatial-Spectral Fusion with Latent Spectral Operators
Solving Stochastic Variational Inequalities without the Bounded Variance Assumption
Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach
Solving Time-Dependent Differential Equations with Physical Dynamical Systems
SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-Body Manipulation
``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
SONAR: Spectral‑Contrastive Audio Residuals for Generalizable Deepfake Detection
Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
SOPE: Situation-Aware and Statistically Indistinguishable Privacy Exfiltration for MCP-enabled Agents
SORA: Free Second-Order Attacks in Fast Adversarial Training
SorryDB: Can AI Provers Complete Real-World Lean Theorems?
SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
Source-Free Open-World RF Fingerprint Identification
SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection
SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
SPADA: A Verifiable Test-Driven Agent for Controllable Parametric CAD Assembly Generation
SpaEF: Spatially Resolved Transcriptomics Data Element-Wise Denoising Framework Powered by Large Models
SpanNorm: Reconciling Training Stability and Performance in Deep Transformers
SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance–Diversity Data Selection
SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents
Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning
Sparse and Faithful Local Explanations with Piecewise Linear Surrogates
(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models
Sparse Autoencoders are Topic Models
Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
Sparse Bayesian Deep Functional Learning with Structured Region Selection
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
SparseInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation
Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training
Sparser Block-Sparse Attention via Token Permutation
Sparse Regression with $\ell_0$ Constraints for $\alpha$-Mixing Time Series: Algorithms and Guarantees
Sparse Relaxed-Lasso Steering: Automatic Sparse Autoencoder Feature Selection for Precise Image Editing
Sparser, Faster, Lighter Transformer Language Models
SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot
Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
Sparse Topology-Aware Pairwise Scoring for Large-Scale Multi-Agent Reinforcement Learning
SPAR: Support-Preserving Action Rectification

« prev Page 106/130 next »