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
Safe In-Context Reinforcement Learning
SafeLab: An Interactive High-Fidelity Benchmark for Embodied Safety in Scientific Robotics
Safe Reinforcement Learning with Preference-based Constraint Inference
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
SafeSeek: Universal Attribution of Safety Circuits in Language Models
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
Safety Alignment of LMs via Non-cooperative Games
Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
Safety-Efficacy Trade Off: Robustness against Data-Poisoning
Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed
Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
SAGE: A Dataflow-Native Framework for Modular, Controllable, and Transparent LLM-Augmented Reasoning
SAGE-NAS: Synergizing LLM-Based Semantic Agent with Graph-Based Evaluator for Neural Architecture Search
SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference
SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling
Saliency-Aware Model Merging
SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos
Salus: Strategic Diagnostic Testing for Complex Diagnosis via Multi-Agent Reinforcement Learning
SAM Audio: Segment Anything in Audio
Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors
Same Question, Different Lies: Cross-Context Consistency (C³) for Black-Box Sandbagging Detection
SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
Sample Complexity Bounds for Robust Mean Estimation with Mean-Shift Contamination
Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation
Sample Margin-Aware Recalibration of Temperature Scaling
Sampling and Identity-Testing Without Approximate Tensorization of Entropy
Sampling from Your Language Model One Byte at a Time
SAMT: Generating Structured Avatar Meshes and Textures from a Single Image
SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
SAQNN: Spectral Adaptive Quantum Neural Network as a Universal Approximator
SARL: Structure-Aligned Reinforcement Learning for Bridging the Perception-Action Gap in Airspace
SARSteer: Safeguarding Large Audio Language Models via Safe-Ablated Refusal Steering
SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
Saving Foundation Flow-Matching Priors for Inverse Problems
SAW-Bench: Learning Situated Awareness in the Real World
SC$^{2}$-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments
Scalable and Differentiable Point-Cloud Registration Using Maximum Mean Discrepancy
Scalable and General Whole-Body Control for Cross-Humanoid Locomotion
Scalable and Interpretable Representation Alignment with Ordinal Similarity
Scalable and Stable Estimation of Amari $\alpha$-Divergence using Random Fourier Features
Scalable Bayesian Inference for Nonlinear Conservation Laws
Scalable Event Cloud Network for Event-based Classification
Scalable GANs with Transformers
Scalable Kronecker-Factored Fisher Approximation for Neural Network Parameter Sensitivity
Scalable Medical Multimodal Fusion via Symmetric Consistency Modeling
Scalable Option Learning in High-Throughput Environments

« prev Page 99/130 next »