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
Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE
Certificate-Guided Pruning for Stochastic Lipschitz Optimization
Certificates for Complex-Compatible Learned Cochain Laplacians
Certified Circuits: Stability Guarantees for Mechanistic Circuits
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
Certifying Capabilities from Finite Tests: When Is It Possible?
Certifying Graph Neural Networks Against Label and Structure Poisoning
Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
CFPO: Counterfactual Policy Optimization for Multimodal Reasoning
CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models
CGRiC: Compositional Risk Certification for Structured LLM Outputs
CGSVD: Cascaded Granular Singular Value Decomposition for Large Language Model Compression
Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding
Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL
Chain-of-Thought Gradient Descent
Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate Forecasting
ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale Awareness
Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization
Characterizing, Evaluating, and Optimizing Complex Reasoning
Characterizing the Effect of Noise in Language Generation in the Limit
Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling
Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment
ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing
Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
CHB: A Diagnostic Toolkit for Hardness-Aware Clustering Evaluation
Cheap2Rich: A Multi-Fidelity Framework for Data Assimilation and System Identification of Multiscale Physics - Rotating Detonation Engines
Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
CHESS: Chebyshev Spectral Synthesis for Trajectory Condensation
Chiral Symmetry Breaking in Transformers: A Group-Equivariant Framework for Addressing the Reversal Curse via Adjoint Manifold Mappings
Chunk-Guided Q-Learning
CINOC: Cardinality-Invariant Neural Operator Policies for Scalable PDE Control
CIRBench: Evaluating Large Language Models as LLVM IR Optimizers
Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Vision-Language Models
CircuitPrint: Mechanistic Circuit Fingerprints for Large Language Models
CiteGuard: Conformal False-Discovery Control for Faithful Retrieval-Augmented Generation
CLAA: Cross-Layer Attention Aggregation for Accelerating LLM Prefill
Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation
CLARITree: Cholesky and Lookahead Accelerations for Regression with Interpretable Piecewise Linear Trees
CLASP: Online learning algorithms for Convex Losses And Squared Penalties
Class-Conditional Distribution Balancing for Group Robust Classification
Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
Class-Prior Perturbation-Robust Regularization for Imbalanced Unreliable Partial Label Learning
CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal
CL-GCL: Comprehensive and Lightweight Graph Contrastive Learning
ClimateAR: Multi-Scale Autoregressive Generative Modeling for Climate Forecasting
CLIMB: Taming the LoRA Residency Cliff in Multi-LoRA Serving
CLINIC : Evaluating Multilingual Trustworthiness in Language Models for Healthcare
CLINIC: Towards High-quality Graph Out-Of-Distribution Detection

« prev Page 19/130 next »