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
Deterministic Component Mining for Multi-Framework UI2Code Generation
Deterministic Differentiable Structured Pruning for Large Language Models
Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch
DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning
DFlash: Block Diffusion for Flash Speculative Decoding
DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation
D-FUSEr: Diverse Failure, Unified Success via Error-Distribution Shaping in LLM Reasoning
DGG-HMR: Multi-Person Human Mesh Recovery with Depth-Guided Geometric Anchoring
dgMARK: Decoding-Guided Watermarking for Diffusion Language Models
DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations
Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory
Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps
DiasR: Dual-Modal Identity-Anchored Sparse Routing for Efficient Multi-Subject Video Generation
Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations
Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
Difference-Aware Decision Learning for Multimodal Image Fusion
Differentiable Conformal Training for LLM Reasoning Factuality
Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control
Differentially Private Continual Release with Relative Error
Differentially Private Cross-Silo Recommendation from Implicit Feedback
Differentially Private Geodesic Regression
Differentially Private Preference Data Synthesis for Large Language Model Alignment
Differentially Private Range Subgraph Counting
Differentially Private Submodular Maximization with a Knapsack Constraint
Differentially Private Synthetic Data via APIs 4: Tabular Data
Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
Differential syntactic and semantic encoding in LLMs
Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations
Diffract: Spectral View of LLM Domain Adaptation
DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization
DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone
DiffuReason: Enhancing Reasoning Ability for Diffusion Language Models via Monte Carlo Tree Search
Diffuse to Detect: Bi-Level Sample Rebalancing with Pseudo-Label Diffusion for Point-Supervised Infrared Small-Target Detection
Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies
Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement
Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis
Diffusion Controller: Framework, Algorithms and Parameterization
Diffusion Differentiable Resampling
Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge
Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions

« prev Page 29/130 next »