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
(Doubly) Exponential Lower Bounds for Follow the Regularized Leader in Potential Games
Doubly Outlier-Robust Online Infinite Hidden Markov Model
Doubly Regularized Markov Decision Processes for Robust Reinforcement Learning
Doubly Robust Distributionally Robust Offline Contextual Pricing
DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMs
Do Vision and Text Cues Exhibit Evidential Coupling? UFO: A Benchmark for Compositional Multimodal Reasoning in Unified Models
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning
DPMI: A Principled Index for Neural Polysemanticity via Dirichlet Process Mixture Modeling
DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and Its Loss' Convexity is Dispensable)
DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole Slide Image Survival Prediction
DR$^2$Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language Models
Draft-and-Audit Reinforcement Learning for Optimization Modeling
DREAM: A Unified Framework for Drift-Corrected Federated Multi-Objective Learning
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
Dreaming in Code for Curriculum Learning in Open-Ended Worlds
Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination
DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution
DRFusion: Drift-Resilient Temporally Consistent Infrared–Visible Video Fusion
DRIFT-BENCH: Diagnosing CoopeRative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
DRIVE: Best Data Scheduling Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation
DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation
DriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
DRL-STAF: A Deep Reinforcement Learning Framework for State-Aware Forecasting of Complex Multivariate Hidden Markov Processes
DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object Detection
Drop-in Circulant Structural Priors for Transformer Decoding of Cyclic Codes
DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting
Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos
DRPBench: Evaluating LLMs in Concurrent Code Comprehension via Fine-Grained Data Race Prediction
DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs
DSENet: A Novel Dual-Stream Enhancement Network for Multi-Scale Non-Stationary Time Series Forecasting
DSGCR: Decomposed Spectral Geometry-Aware Cross-Modal Semantic Representation for 3D Visual Grounding
DSGym: A Holistic Framework for Evaluating and Training Data Science Agents
DSGym: A Standardized and Holistic Framework for Evaluating and Training Data Science Agents
DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training
dTRPO : Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
Dual-branch Robust Unlearnable Examples
Dual-Calibration Multi-View Clustering via Compact Anchor Learning
Dual-channel Dynamic Graph Neural Networks with Adaptive Adjacency Learning and Multi-scale Representation Fusion
DualCOIL: Offline Imitation Learning from Contrasting Demonstrations
Dual Latent Memory for Visual Multi-agent System
Dual-Latent Memory Routing for Vision-Language Reasoning

« prev Page 33/130 next »