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
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Spatial Conformal Inference through Localized Quantile Regression
Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference
SpatialJB: How Text Distribution Art Becomes The "Jailbreak Key" for LLM Guardrails
Spatially-Adaptive Gradient Re-parameterization for 3D Large Kernel Optimization
Spatially-Regularized Entropy for Discriminative Token Merging in Fine-Grained Re-Identification
Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action
Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers
SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes
SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models
Spatiotemporal Imputation with Graph-Informed Flow Matching
Spatio-Temporal LLM: Reasoning about Environments and Actions
SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
SpecExit: Accelerating Large Reasoning Model via Speculative Exit
SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
SpecMD: A Comprehensive Study On Speculative Expert Prefetching
SpecPL: Disentangling Spectral Granularity for Prompt Learning
SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
Spectral Bridge Variational Inference: Dynamic LoRA via Bures-Wasserstein Gradient Flows
Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
Spectral Flow Matching: Stabilizing Stochastic GFlowNets via Frequency-Domain Regularization
Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
Spectral Guidance for Flexible and Efficient Control of Diffusion Models
Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models
Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
Spectral-Informed Neural Networks Outperform Spectral methods in High-dimensional PDEs
Spectrally-Guided Diffusion Noise Schedules
Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoning
Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy
Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks
Speculative Sampling For Faster Molecular Dynamics
Speech-Audio Compositional Attacks on Multimodal LLMs and Their Defense with SALMONN-Guard
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
SpeedCP: Fast Kernel-based Conditional Conformal Prediction
SPEED: Sharpened-Teacher Distillation for Parallel Decoding of Diffusion Language Models
Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
SpeedVFI: One-step Diffusion for Efficient Video Frame Interpolation
SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
SphericalDreamer: Generating Navigable Immersive 3D Worlds with Panorama Fusion
Spherical Procrustes Alignment for Reliable Medical Audio Diagnosis
Spherical SO(3) Equivariant Local Attention
Spherical Steering: Geometry-Aware Activation Rotation for Language Models
Spik4lite: Refactoring Neuromorphic Sparsity for Efficient Spiking Neural Networks on Commodity Edge Devices
Spike Camera Autofocus via Frequency-Domain Spectral-Centroid Migration
SpikeCLR: Self-Supervised Contrastive Learning for Visual Representations with Spiking Neural Networks
Spiked-CFR: Causal Representation Learning from LLMs via Wasserstein Projection Pursuit

« prev Page 107/130 next »