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
Hyperparameter Transfer with Mixture-of-Expert Layers
Hyperparameter Transfer with Mixture-of-Experts Layers
HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism
HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation
HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds
HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
IACW: Intent-Aware Controllable Watermarking for Scalable Authorial Intent Attribution
IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
IBMA: Information Bottleneck-Based Multimodal Alignment
ICR-RL: Deep Reinforcement Learning via In-Context-Regression
Ideal Attribution and Faithful Watermarks for Language Models
Identifiable Equivariant Networks are Layerwise Equivariant
Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families
Identifiable Nonlinear Differentiable Causal Discovery via Independence and Adaptive Group Sparsity
Identifiable Smooth Conjugacy Learning via Adversarial Orthogonality
Identifiable Token Correspondence for World Models
Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction
Identifying and Mitigating Errors in Gradient Aggregation of Distributed Data Parallel Training
Identifying Common Hubs in Multiple Gaussian Graphical Models
Identifying Connectivity Distributions from Neural Dynamics Using Flows
Identifying dependent components from multi-domain linear mixtures
Identifying Latent Concepts and Structures for Generalized Category Discovery
Identifying Learnwares via Reduced Neural Conditional Mean Embedding
Identifying Partially Observed Causal Models from Heterogeneous/Nonstationary Data
IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension
IDLM: Inverse-distilled Diffusion Language Models
IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research
IEC: When Information-Driven Exploration Meets Spectral Consensus via Primal–Dual Reward Regularization in Decentralized Multi-Agent RL
iGRPO: Fast Online RL for Flow Matching Model with Instant Reward
iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
Image Restoration via Diffusion Models with Dynamic Resolution
Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models
Imagination Helps Visual Reasoning, But Not Yet in Latent Space
ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model
Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections
ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning
Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness
IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection
Impact of Connectivity on Laplacian Representations in Reinforcement Learning
Implicit Action Chunking for Smooth Continuous Control
Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
Implicit Intelligence - Evaluating Agents on What Users Don’t Say
Implicit Preference Alignment for Human Image Animation
Implicit Safety Alignment from Crowd Preferences
Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction
Imposing Boundary Conditions on Neural Operators via Learned Function Extensions
ImpQuant: Fine-Grained Importance-Aware Quantization for Large Vision-Language Models
Improved Algorithms for Nash Welfare in Linear Bandits
Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA

« prev Page 55/130 next »