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
Reliable Neighborhood-Aware Multi-View Outlier Detection
Reliable Thinking with Images
Relighting as a Probe of Visual Priors via Augmented Latent Intrinsics
Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases
RELO: Reinforcement Learning to Localize for Visual Object Tracking
ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference
Remove the Ambiguity: Few-shot Multimodal Anomaly Detection Using Crossmodal Feature Replacer
Remove the Ambiguity: Few-shot Multimodal Anomaly Detection Using Crossmodal Feature Replacers
Removing Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining
Removing Sandbagging in LLMs by Training with Weak Supervision
ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters
Rényi Diffusion Models
RePack then Refine: Efficient Diffusion Transformers with Vision Foundation Models
Reparameterization Flow Policy Optimization
Reparameterization Proximal Policy Optimization
RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress
rePIRL: Learn PRM with Inverse RL for LLM Reasoning
Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
RePo: Language Models with Context Re-Positioning
Representational Curvature Modulates Behavioral Uncertainty in Large Language Models
Representational Similarity and Model Behavior in Multi-Agent Interaction
Representation Drift Compensation: A Near-Zero Inference Cost Enhancement for LLM Decomposition
Representation Learning for Equivariant Inference with Guarantees
Representation Unlearning: Forgetting through Information Compression
RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training
Required Spine Optional Limbs: Heterogeneous Federated Learning via Backbone-sharing and Activation-guided Selection
Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against Retrieval-Augmented Generation
ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
Residual Context Diffusion Language Models
Residual-Guided Multi-Resolution Refinement of Foundation Models: A Case Study in Drought Forecasting
Resilient Coresets and Clustering
Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-Identification
Resolving Blind Inverse Problems under Dynamic Range Compression via Structured Forward Operator Modeling
Resolving the Timestep Scaling Paradox in Spiking Neural Networks with a Timestep-Scalable Neuron Model
Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models
ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation
Responsible Text-to-Image Diffusion: Interpretable and Linearly Controllable Semantics for Fair and Safe Generation
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation
Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models
Restoring Initial Noise Sensitivity in Text-to-Image Distillation through Geometric Alignment
Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment
ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning
Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models
Rethinking 3D Shape Generation: Diffusion over Superquadrics
Rethinking Attention in Spiking Transformers: Overcoming Density Bias with Set Similarity

« prev Page 94/130 next »