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
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping
Memory as Dynamics: Learning Reliability-Guided Predictive Models for Online Video Perception
MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
Memory Caching: RNNs with Growing Memory
Memory-Distilled Selection for Noise-Robust Anomaly Detection
Memory-Efficient LLM Pretraining via Minimalist Optimizer Design
Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers
Memory Savings at What Cost? A Study of Alternatives to Backpropagation
*MemPot*: Defend Against Memory Extraction Attack with Optimized Honeypots
MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
Mem-T: Densifying Rewards for Long-Horizon Memory Agents
MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
MER-DG: Modality-Entropy Regularization for Multimodal Domain Generalization
MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
Merge to Remember: Sharpness-Aware Isotropic Merging for Continual Learning
MESA: Improving MoE Safety Alignment via Decentralized Expertise
Mesh Based Simulations with Spatial and Temporal awareness
Mesh Field Theory: Port–Hamiltonian Formulation of Mesh-Based Physics
MeshTok: Efficient Multi-Scale Tokenization for Scalable PDE Transformers
Message Passing on the Edge: Towards Scalable and Expressive GNNs
Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective
Meta-Black-Box Optimization Can Do Search Guidance for Expensive Constrained Multi-Objective Optimization
Meta Context Engineering via Agentic Skill Evolution
MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Metadynamics
MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics
Meta Flow Maps enable scalable reward alignment
Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics Environments
Meta-learning Structure-Preserving Dynamics
MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
MetaOthello: A Controlled Study of Multiple World Models in Transformers
MetaPerch: Learning from metadata for bioacoustics foundation models
MetaphorVU: Towards Metaphorical Video Understanding
MetaStreet: Semi-Supervised Multimodal Learning for Street-Level Socioeconomic Prediction
MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
Metric—Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point Clouds
MFH-NAS:A Hybrid Neural Architecture Search Framework for Multimodal Fusion Object Detection
MGAL: A Multilingual Granularity-Aware Long-Context Benchmark
mHC: Manifold-Constrained Hyper-Connections
MICE-Bench: A Challenging and Comprehensive Benchmark for Multi-Reference Image Creation and Editing
M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model
MidSteer: Optimal Affine Framework for Steering Generative Models
Midtraining Bridges Pretraining and Posttraining Distributions
Milestone-Guided Policy Learning for Long-Horizon Language Agents
MIMO-LP: A Multi-Input Multi-Output Framework for Subgraph-based Link Prediction

« prev Page 70/130 next »