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
Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?
DiLA: Disentangled Latent Action World Models
DiL: Discrete-anchored Representation Alignment for Semi-Supervised Continual Learning
Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
Dimensionality Reduction with Point-Distribution Similarity Invariant
Dimensionality Reduction with Point-distributions Similarity Invariant
Dimension-free convergence of diffusion models for approximate Gaussian mixtures
Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin Dynamics
Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
DiP-G: Discrete Prompting for Graph Neural Networks
Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing
Direct Flow Q-Learning
Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning
Directly Optimizing Natural Language Explanations for Behavioral Faithfulness: Simulatability and Recoverability
Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing
DiScoFormer: Plug-In Density and Score Estimation with Transformers
DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring
Discounted Beta–Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards
Discovering Differences in Strategic Behavior between Humans and LLMs
Discovering Implicit Large Language Model Alignment Objectives
Discovering Interpretable Algorithms by Decompiling Transformers to RASP
Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks
Discovering Symmetry Groups with Flow Matching
DiscoverLLM: From Executing Intents to Discovering Them
Discover then Refine: A Joint Multiple Choice Learning and Flow Matching Framework for Heat Demand Forecasting
Discrete Adjoint Schrödinger Bridge Sampler
Discrete Diffusion Samplers and Bridges: Off-Policy Algorithms and Applications in Latent Spaces
Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
Discrete Diffusion with Physical Mass Constraints for \emph{De Novo} Peptide Sequencing
Discretely-Refined Multi-view Clustering via Aligned Anchor Learning
Discrete Survival Knowledge Distillation for Competing Risks Analysis
Discrete Tilt Matching
Discretized Density-Guided Source-Free Domain Adaptation for Regression
Discriminative Attribute Graph Clustering Through Topology-Guided Contrastive Learning
Discriminative Mixture-of-Experts on Graphs with Reliable Expert Fusion
Discriminative Visual Process Rewards for Scaling Thinking at Test-Time with Images
Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography
Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment in LLMs
Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs
Disentangling Geometry, Performance, and Training in Language Models
Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference
DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
Dismantling the Illusion of Vision-Language-Action Models Competence via Explicit Distributional Shifts
Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models

« prev Page 30/130 next »