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
A Perturbation Approach to Unconstrained Linear Bandits
APEX: Approximate-but-exhaustive search for ultra-large combinatorial synthesis libraries
API: Adaptive Prototype Imputation for Incomplete Multimodal Sentiment Analysis
APIC: Orthogonalized Neuro-Symbolic Modeling for Nonlinear Dissipative Dynamics
A Positive Case for Faithfulness: Explanations Help Predict Model Behavior
A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
Approximate Equivariance via Projection-Based Regularisation
Approximate Nearest Neighbor Search for Modern AI: A Projection-Augmented Graph Approach
Approximate Proportionality in Online Fair Division
Approximating Drift-Diffusion Models for User Decisions under Nudging and External Information
Approximating f -Divergences with Rank Statistics
Approximation Bounds for Transformer Networks with Application to Regression
Approximation Error Upper and Lower Bounds for Hölder Class with Transformers
Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training
Approximation Preserving Coresets
Approximation Theory for Lipschitz Continuous Transformers
AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
A Probabilistic Framework for LLM-Based Model Discovery
A Progressive Evidence Localization Framework Based on Wasserstein Gradient Flows for Document Visual Question Answering
A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention
A proximal ADMM for multiblock problems with block anti-upper triangular constraints
A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
A Random Matrix Perspective on the Consistency of Diffusion Models
A Random Matrix Theory of Masked Self-Supervised Learning
A Random Matrix Theory Perspective on the Consistency of Diffusion Models
Arboreal Neural Network
ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning
ArcDAE: Asymmetric Rectified Contrastive Diffusion Autoencoder for Unified Representation Learning
ARC-Decode: Accelerated Decoding with Risk-Bounded Acceptance
Architecture Matters for Multi-Agent Security
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
AReaL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
A recipe for scalable attention-based ML potentials: unlocking long-range accuracy with all-to-all node attention
Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles
A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables
A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning
Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach
A Regime-Aware Trajectory Prediction Framework for 1000+ Systems Biology Models
A Regret Minimization Framework on Preference Learning in Large Language Models
Are Large Reasoning Models Interruptible?
Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Are Object-Centric Representations Better at Compositional Generalization?
Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach
Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination
Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation?
Are Your Agents Upward Deceivers?
Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses

« prev Page 8/130 next »