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
Parametrized Power-Iteration Clustering for Directed Graphs
ParamMem: Augmenting Language Agents with Parametric Reflective Memory
ParaTool: Shifting Tool Representations from Context to Parameters
Pareto-Guided Optimal Transport for Multi-Reward Alignment
ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
Parsimonious Learning-Augmented Online Metric Matching
PartCo: Part-Level Correspondence Priors Enhance Category Discovery
Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
Partial Identification of Policy Values under Network Interference
Partial Identification under High-Dimensional Potential Outcomes and Confounders via Optimal Transport
Partial Ring Scan: Revisiting Scan Order in Vision State Space Models
Particle Flow for Learning from Label Proportions
Particle-Guided Diffusion Models for Partial Differential Equations
Particles Don’t Care About Z: Towards Scaling Entropy Estimation of Unnormalized Densities
Partitioning for Intrinsic Model Inversion Resistance in Collaborative Inference
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
PASO: Step Parallel Stochastic Optimization
PATCHCODE: Discrete Latent Predictive Learning for EEG Foundation Model
Path-conditioned training: a principled way to rescale ReLU neural networks
Path-Coupled Bellman Flows for Distributional Reinforcement Learning
Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation
Path-dependent Discrete Amortized Inference
PathwayLLM: Explainable Clinical Trajectory Modeling with Structured Pathways for Sepsis Prediction
PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
Patterning: The Dual of Interpretability
PatternKV: Flattening KV Representation Expands Quantization Headroom
PAWS: Preference Learning with Advantage-Weighted Segments
PCA of Probability Measures: Sparse and Dense Sampling Regimes
PCGS: Deblurring 3D Gaussian Splatting with Patch Comparison
PCRNet: Phase-aware Complex Refinement Network for EEG-based Auditory Attention Decoding
PDAgent: An LLM-Driven Autonomous Agent Framework Towards *In Silico* Protein Design via Directed Mutation
PDFBench: A Benchmark for De Novo Protein Design from Function
PEARL: Differentially Private and Entropy-Aware Regulated Language Generation
Peer-Preservation in Frontier Models
PepCompass: Navigating Peptide Embedding Spaces Using Riemannian Geometry
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
Perceptrons and Localization of Attention’s Mean-Field Landscape
Perceptual Flow Network for Visually Grounded Reasoning
Per-example Gradients: a New Frontier for Understanding and Improving Optimizers
Performative Learning Theory
Performative Policy Gradient: Optimality in Performative Reinforcement Learning
Periodic Bayesian Flow Networks with Additive Accuracy
PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
Persistent Backdoor Attacks in Class-Incremental Learning via Structural Invariant Anchoring
Persistent Semantic Entities in Tool-Augmented LLM Systems
Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
Personalized Additive Modeling for Multi-level Federated Learning
Personalized Image Generation via Human-in-the-loop Bayesian Optimization

« prev Page 83/130 next »