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
CRAG: Can 3D Generative Models Help 3D Assembly?
CRAMER: Control via Request-Aware Masking for Editing Recommenders
Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
Creat3r: Confidence Reaggregation for Exploration-aware Active 3D Reconstruction
Credibility-Aware Weighting Federated Causal Discovery for Time Series
Credible Information Subset Decomposition: An End-to-End Multi-fidelity Learning Model by Modeling Label Information
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
Credit Assignment via Neural Manifold Noise Correlation
CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks
Crisp: A Spectral-Based Interaction Strategy for Multivariate Time Series Forecasting
CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing
Criterion-Conditional In-Context Learning: Evaluating Criterion-Shift Adaptation in Vision-Language Models
CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective
Critique-Guided Distillation for Robust Reasoning via Refinement
Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design
Cross-Embodiment Robot Foundation World Models with Latent Actions
Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
Cross-Modal Semantic Decoupling and Transfer for Text-to-Visible-Infrared Person Re-Identification
CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction Retrieval
Cross-Subject Modeling for Widefield Calcium Imaging via Atlas-Aligned Spatiotemporal Tokenization
Cross-Tactile Sensor Representation Learning
Cross-task Calibration for Asynchronous Federated Continual Learning
Cross-View Lewis Weight Fusion Empowering Exemplar Replay for Federated Class-Incremental Learning
Crowd4D: Scene-Aware Monocular 4D Crowd Reconstruction
CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents
CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EM
CSD: Content-aware Speculative Decoding for Efficient Image Generation
CSG: Cognitive Structure Generation for Intelligent Education
CSOR: Coreset Selection for Object Re-identification via Class Pruning
CSPLoRA: Confidence-Guided Structural Planning for Low-Rank Adaptation
CSPLoRA: Confidence-Guided Structure Planning for Low-Rank Adaptation
CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning
CUARewardBench: A Benchmark for Evaluating Reward Models for Computer-Using Agents
CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM
Curated Synthetic Data Doesn’t Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
Curating the Future: A Scalable Recipe for Training Open-Ended Forecasters
CURE: Consistency-under-Unified Semantic Regularization for Generalized Category Discovery
CURE: Context-driven Diffusion with Progressive Expansion for Single Domain Generalization in Time Series Classification
cuRegOT: A GPU-Accelerated Solver for Entropic-Regularized Optimal Transport
Cure-SFT: Diagnostic-Guided Data Curation for Instruction Tuning
Curriculum-Guided Layer Scaling for Language Model Pretraining
Curriculum Reinforcement Learning for Black-Box Prompt Tuning via Large Language Models
CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularization
CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm That Provably Exploits Model Similarity
CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception
CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities
CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict
Cycle-of-Science: Reliable Reasoning through Counterfactual Verification for Agent Decision Making

« prev Page 25/130 next »