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
Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in Large Language Models
Dual Optimal Transport for Multi-Concept Composition: Structural Alignment and Texture Injection in Diffusion Models
Dual Optimal Transport for Multi-Concept Composition: Structure Alignment and Texture Injection in Diffusion Models
DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
Dual Quaternion SE(3) Synchronization with Recovery Guarantees
Dual-stage Contrastive Learning-enhanced Multi-view Variational Clustering
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
DualTimesField: Rethinking Time Series as Continuous-Time Trends and Events
Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy
DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing
DuRP: Dual-Stage Physics-Embedded Learning for Joint Radiance and Polarization Restoration
Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling
DyGRO-VLA: Cross-Task Scaling of Vision–Language–Action Models via Dynamic Grouped Residual Optimization
DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention
DynaMem: Consistent Long Video Generation via Hierarchical Memory and Motion Priors
Dynamic Compression Flows for Neuroscience Data
Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases
Dynamic Fractal Mamba: A Neural Renormalization Group Flow for Scale-Invariant Sequence Modeling
Dynamic High-Dimensional Facility Location with Low Recourse
Dynamic Linear Attention
Dynamic Multimodal Evaluation via Knowledge-Enhanced Benchmark Evolution
Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents
Dynamic Programming for Epistemic Uncertainty in Markov Decision Processes
Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer
Dynamic Relational Priming Improves Transformer in Multivariate Time Series
Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks
Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation
Dynamics of neural scaling laws in random feature regression with powerlaw-distributed kernel eigenvalues
Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
Dynamic Stratified Contrastive Learning with Upstream Augmentation for MILP Branching
Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training
Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting
DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents
DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics
DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving
Dyn-VPP: Video Prediction Policy Optimization for Improved Visual Dynamics
DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion
Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals
E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory
E²I-VRWKV: Explicit EPI-Representation and Interaction-Aware Vision-RWKV for Light Field Semantic Segmentation
EAGer: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling
EAKV: An Entropy-Driven Adaptive KV Compression Framework for Long Video Understanding
EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance
EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding
Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models

« prev Page 34/130 next »