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
Wait, Wait, Wait... Why Do Reasoning Models Loop?
Walrus: A Cross-domain Foundation Model for Continuum Dynamics
WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
Wasserstein Geometry-Aware Adaptive Control via Meta-Learning
WatchLog: Efficient and Interpretable Event Reasoning for Endpoint Detection and Response Logs with Multimodal LLMs
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
Watermarking Graph Neural Networks via Explanations for Ownership Protection
Watermarking LLM Agent Trajectories
WaterSIC: Information-Theoretically (Near) Optimal \\Linear Layer Quantization
WaveSSM: Multiscale State-Space Models for Non-stationary Signal Attention
WAVE: Window-Aware Vocabulary-Efficient Early-Exit for Training-Free LLM Acceleration
WBMM: Windowed Batch Matrix Multiplication for Efficient Large Receptive Field Convolution
Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance
Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation
Weak-to-Strong Generalization via Bregman Bias–Variance Decomposition
Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection
WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation
Weaving Graph over Tokens: Contextualizing Structured Sequences for LLMs
Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated Learning
WebWorld: A Large-Scale World Model for Web Agent Training
WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference
WeightCLIP: Aligning Datasets and Models for Weight Space Learning
Weight Decay Improves Language Model Plasticity
Weight-Space Learning for Certifiable Few-shot Transfer Learning
Weight-sparse transformers have interpretable circuits
Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer
Weight Updates as Activation Shifts: A Principled Framework for Steering
Welfare-Optimal Classification with Accuracy Auctions
Well-Posed KL-Regularized Control via Wasserstein and Kalman–Wasserstein KL Divergences
WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems
WET: Mitigating World-Conditioned Knowledge Conflicts via World Entropy Tethering
WEVSR: Video Diffusion Generators for Real-World Video Super-Resolution with Wavelet-Enhanced VAE Encoder
WF-Bench: A Benchmark for Neural-Network WaveFunction Expressivity and Scaling Laws
WFR-MFM: One-Step Inference for Dynamic Unbalanced Optimal Transport
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?
What Does Flow-Matching Bring to TD-Learning?
What Does Preference Learning Recover from Pairwise Comparison Data?
What Does Thompson Sampling Optimize?
What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom
What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
What If We Allocate Test-Time Compute Adaptively?
What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition
What is Missing? Explaining Neurons Activated by Absent Concepts
What Language is This? Ask Your Tokenizer.
What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
What LLMs Explain Is Not What They Believe: Evaluating Explanation Sufficiency Under Models' Own Input Beliefs
What Makes a Desired Graph for Relational Deep Learning?
What Makes a Representation Good for Single-Cell Perturbation Prediction?

« prev Page 127/130 next »