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
Sharp Inequalities between Total Variation and Hellinger Distances for Gaussian Mixtures
Sharpness-Aware Minimization Can Hallucinate Minimizers
Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
SHARP-Q: Spectral Hessian Alignment and Rectification for Post-training Quantization
Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning
SHERPA: Fine-tuning Segment Anything Models with Task-relevant Guidance
Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
Shifting the Breaking Point of Flow Matching for Multi-Instance Editing
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization
Shortcut-Resistant CAM Distillation for Long-Tailed Recognition
Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates
Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control
Show, Don't Tell: Morphing Latent Reasoning into Image Generation
Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards
Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation
Shuffling-Aware Optimization for Private Vector Mean Estimation
SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model
Signal Strength Estimation in Logistic Regression Using Data Splitting
Signature-Informed Transformer for Asset Allocation
Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
SI-IGCL: Subject Invariance-aware Inverse Graph Contrastive Learning for Psychiatric Disorder Identification
SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning
Sim2Reason: Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
SimGFM: Simplifying Discrete Flow Matching for Graph Generation
Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models
SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising
Simple Algorithms for Bad Triangle Transversals with Applications to Correlation Clustering
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
Simple Denoising Diffusion Language Models
SimpleGPT: Improving GPT via A Simple Normalization Strategy
SimpleMem: Efficient Lifelong Memory for LLM Agents
Simple Policy Gradients for Reasoning with Diffusion Language Models
Simple yet Effective: Low-Rank Spatial Attention for Neural Operators
SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs
Simultaneous Confidence Bounds for Aggregated Effects via Exact Subset Optimization
Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Simultaneous Speech-to-Speech Translation Without Aligned Data
Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection
Singular Bayesian Neural Networks
Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
Singular Proxies for Adaptive Caching in Diffusion Language Models
Singular Vectors of Attention Heads Align with Features
Sinkhorn Normalization of Diffusion Kernels
Sinkhorn Treatment Effects: A Causal Optimal Transport Measure
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion Models
Size Transferability of Graph Convolutional Networks across Sparsity: A Generalized Graphon Perspective

« prev Page 104/130 next »