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
Beyond Detection: A Structure-Aware Framework for Scene Text Tracking
Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning
Beyond Drift: Stabilizing Subjective LLM Evaluation with Information-Theoretic Rubrics
Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
Beyond Euclidean Summaries: Online Change Point Detection for Distribution-Valued Data
Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs
Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting
Beyond First-order Asymptotics in Sequential Mean Testing
Beyond Fixed Biases: Decoding the Role of Reasoning Uncertainty in MLLM Modality Conflicts
Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale
Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning
Beyond Hamming: Query-Aware Decoding of Binary Cosine Sketches
Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
Beyond Independence: Learning Correlated Views for Variational Incomplete Multi-View Clustering
Beyond Independent Genes: Learning Module-Inductive Representations for Single-Cell Gene Perturbation Prediction
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
Beyond Language Modeling: An Exploration of Multimodal Pretraining
Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC
Beyond Logits: Coherent Hallucination Mitigation via Attention Contrastive Decoding
Beyond Logits: Metastable Latent Dynamics for Sample-Efficient Best-of-N Selection in LLMs
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering
Beyond Magnitude: Scale-Invariant Evidential Fusion for Multi-View Classification
Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
Beyond Majority Voting: Self-Reflective Test-Time Reinforcement Learning for LLM Reasoning
Beyond Mode Collapse: Distribution Matching for Diverse Reasoning
Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design
Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting
Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR
Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models
Beyond Pixel Histories: World Models with Persistent 3D State
Beyond Pixels: Mining Compressed Domain Artifacts for Efficient AI-Generated Video Detection
Beyond Point Predictions: Manifold Expansion and Dual Alignment for Robust Time Series Distillation
Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning
Beyond Policy Training: Recursive Solution Search from Unannotated Videos
Beyond Prediction: Tail-Aware Scheduling for LLM Inference
Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
Beyond Procedure: Substantive Fairness in Conformal Prediction
Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
Beyond Reactivity: Proactive Adaptive Conformal Inference for Online LLM Factuality
Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors
Beyond Rewards in RL for Cyber Defence
Beyond Sample-Level Forgetting: Improving Reliability in Multimodal Unlearning
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
Beyond Single Embedding: Modeling User Preferences as Distribution in Federated Recommendation
Beyond Single-View Indexing: Structure-Aware Multi-View Retrieval for Knowledge-Based VQA

« prev Page 13/130 next »