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
D$^2$O: A Dual Debiasing Operator for Training-Free Test-Time Adaptation of Vision–Language Models
d$^2$p: Structured Soft Attention Is All You Need
D$^3$: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training
D²Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation
d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
DADP: Domain Adaptive Diffusion Policy
DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants
DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits
DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs
DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
D-ARL: A Distribution-Matched Asynchronous Reinforcement Learning Framework for Language Reasoning
DART: Distribution-Aware Adaptive Relational Transfer for Adversarial Attacks against Closed-Source MLLMs
DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution
DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers
Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise
Data Difficulty and the Generalization–Extrapolation Tradeoff in LLM Fine-Tuning
Data-driven Mixed Integer Optimization through Probabilistic Multi-variable Branching
DataGuard: A Non-intrusive Dataset Auditing Framework via Differential Information Forensics
Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
Data Reconstruction: Identifiability and Optimization with Sample Splitting
Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories
Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
Data-Source Adaptive Online Learning under Heteroscedastic Noise
DAVE: Distribution-Aware Attribution via ViT Gradient Decomposition
daVinci-Dev: Agent-native Mid-training for Software Engineering
DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
DC-LA: Difference-of-Convex Langevin Algorithm
DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding
D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use
DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning
DDGA: Dirichlet Distributional Gradient Aggregation for Transferable Vision-Language Adversarial Attacks
DDIM Inversion as a Perturbation Amplifier: Breaking Mimicry Protection via Reconstruction Error Minimization
DDP-WM: Disentangled Dynamics Prediction for Efficient World Models
DDSVM: A Differentiable Framework for Deep Support Vector Machines with Iterative Geometry-Aware Optimization
De4D-SLAM: Gradient-Isolated Static-Dynamic Decoupling for Monocular SLAM in Dynamic Environments
De-attribute to Forget for LLM Unlearning
Debate2Create: Robot Co-design via Multi-Agent LLM Debate
Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
Debiased Model-based Representations for Sample-efficient Continuous Control
DecAEvolve: Decompose, Adapt, and Evolve for Effective LLM-based Scientific Equation Discovery
Decentralized and Disentangled Task–Role Representation Learning for Generalizable Offline Multi-Agent Meta Reinforcement Learning
Decentralized Bandits without Global Clock for Dynamic Matching Market
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging

« prev Page 26/130 next »