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
MIMOMamba: From Scalar Duality to Matrix-Valued Attention
MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds
MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation
MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models
Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion
Mind the Budget: Accelerating Deep Reinforcement Learning using Constrained Early Exit Neural Networks
Mind the Gap: Catching Hallucinations via Evidence Drop on the Reasoning Manifold
Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
Mind the Gap: Structure-Aware Consistency in Preference Learning
Mind the State: Towards Unified, Context-Aware EEG-to-fMRI Synthesis
Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
MindZero: Learning Online Mental Reasoning With Zero Annotations
MineDraft: A Framework for Batch Parallel Speculative Decoding
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching
Minibatch selection for Language Models via Partition Matroid Constrained Gradient Matching
miniF2F-Dafny: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification
MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification
Minimax-Optimal Policy Regret in Partially Observable Markov Games
Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning
Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection
Minimizing Upper Confidence Bounds: A Data-Driven Framework for Stochastic Programming
MINIM: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization
Minimum Distance Summaries for Robust Neural Posterior Estimation
Mining Tensor/Neuron-Level Sparsity to Maximize Mixture-of-Experts Potential in Post-Training and Inference
Mining Useful General Data for Low-Resource Domain Adaptation
MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation
MIRA: A Score for Conditional Distribution Accuracy and Model Comparison
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency
Mirror Descent Actor Critic via Bounded Advantage Learning
Mirror Descent Under Generalized Smoothness
Mirror Mean-Field Langevin Dynamics
MIST: Moment-Aligned Invariant Stability Transform for Robust Flow Matching
Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
Mitigating Conversational Inertia in Multi-Turn Agents
Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering
Mitigating Error Propagation in Low-Rank Approximation of Large Models via Distribution-Aware Whitening
Mitigating Gradient Pathology in PINNs through Aligned Constraint
Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating
Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding
Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models
Mitigating Noise-Induced Layout Priors for Object Counting in Diffusion Models
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
Mitigating Plasticity Loss through Architectural Design in Continual Learning
Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
Mitigating Reward Hacking in LLM-based Recommendation: A Preference Optimization Approach
Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling

« prev Page 71/130 next »