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
Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models
Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction
Deep sequence models tend to memorize geometrically; it is unclear why
DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
Deep Single-Index Fréchet Regression
Deep Trajectory Supervision: Deep Supervision Strikes Back
DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation
DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
Deformba: Vision State Space Model with Adaptive State Fusion
DEGAP: Dynamic Entropy-Guided Attention Perturbation for Contrastive Decoding in Large Vision-Language Models
Degradation-Aware Metric Prompting for Hyperspectral Image Restoration
Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation
Delegation and Verification under AI
Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs
De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution
DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution
Delving into Muon and Beyond: Deep Analysis and Extensions
Delving into Non-Exchangeability for Conformal Prediction in Graph-Structured Multivariate Time Series
Demystifying Action Space Design for Robotic Manipulation Policies
Demystifying Entropy Control in LLM RL Training: Theoretical Analysis and Dynamic Scheduling
Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success
Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning
Demystifying the Optimal Fair Classifier in Multi-Class Classification
Demystifying When Pruning Works via Representation Hierarchies
Denoising without Diffusion: Fixed-Noise Denoiser Anomaly Detection in Tabular Data
Dense associative memory for Gaussian distributions
DenseMLLM: Standard Multimodal LLMs for Dense Prediction
DenseSteer: Steering Small Language Models towards Dense Math Reasoning
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity
Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies
Depth-Progressive Monotonic Learning without Global Backpropagation
Derivative Informed Learning of Exchange-Correlation Functionals
Deriving Neural Scaling Laws from the Statistics of Natural Language
Design-Based Anytime-Valid Inference for Randomized Experiments with Delayed Outcomes and Staggered Entry
Designing Observation and Action Models for Efficient Reinforcement Learning with LLMs
Design Linear Constrained Neural Layers with Implicit Convex Optimization
Desirable Effort Fairness and Optimality Trade-offs in Strategic Learning
Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR
DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation
Detecting Contextual Hallucinations in Large Language Models with Frequency-Aware Attention
Detecting Errors in AI-Generated Annotations: When and Why Semantic Neighbors Help
Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes
Detecting Perspective Shifts in Multi-Agent Systems
Detecting the Semantic Fixed Point: A Geometric Framework for Efficient Inference

« prev Page 28/130 next »