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
Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
Expected Returns and Policy Inconsistency-Aware Offline Federated Deep Reinforcement Learning
Experience Augmented Policy Optimization for LLM Reasoning
Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic–Procedural Memory
Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs
Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration
Expert-level Leaf Cell Layout Generation via Preference-Optimized LLM
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns
Explainable Federated Learning via Global–Local Attribution Alignment
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
Explaining Concept Shift with Interpretable Feature Attribution
Explaining Data Mixing Scaling Laws
Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
Explicitly Modeling Censoring Produces Superior Survival Predictors
Explicit representation of germline and non-germline residues improves antibody language modeling
Exploiting weight-space symmetries for approximating curvature
Exploration-free Algorithms for Multi-group Mean Estimation
Exploration Hacking: Can LLMs Learn to Resist RL Training?
Exploring 3D Dataset Pruning
Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference
Exploring and Exploiting Stability in Latent Flow Matching
Exploring Data-Free LoRA Transferability for Video Diffusion Models
Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance
Exploring Motif-based Heterogeneous Graph Learning for ReDoS Detection
Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning
Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic Range
Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks
Expressive Graph Neural Networks via Equivariant Use of Noise
Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models
ExpWeaver: LLM Agents Learn from Experience via Latent RAG
Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methods
Extending Prediction-Powered Inference through Conformal Prediction
Extracting alignment data in open models
Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
ExVerus: Verus Proof Repair via Counterexample Reasoning
Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors
FAB: A First-Order AB-based Gradient Algorithm for Distributed Bilevel Optimization over Time-Varying Directed Graphs
FACT: Fuzzy Alignment with Comorbidity Topology for Reliable Multi-Label Medical Image Diagnosis
FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning
Factored Causal Representation Learning for Robust Reward Modeling in RLHF
Factored Classifier-Free Guidance
Factored Gossip DiLoCo: Reducing Blocking Communication in DiLoCo
Factored Gossip DiLoCo: Reducing Blocking Communication within DiLoCo
Factored Latent Action World Models
Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning
Factorized Scheduling Principle: Learning Interpretable and Transferable Policies via Structured Additive Functions
Factor-Wise Homogeneity of Slot-Attention for Continual Object-Centric Learning

« prev Page 40/130 next »