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
InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation
Interleaved Selective State Space Models for Efficient WiFi-Based 3D Multi-Person Pose Estimation
Internalizing Safety Understanding in Large Reasoning Models via Verification
Interpretability and Generalization Bounds for Learning Spatial Physics
Interpretability Driven Evolutionary Approach for the Design of Biological Sequences
Interpretability Transfer from Language to Vision via Sparse Autoencoders
Interpretable Discovery of One-parameter Subgroups: A Modular Framework for Elliptical, Hyperbolic, and Parabolic Symmetries
Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
Interpretable Functional Koopman Learning with Non-Markovian Closure for Spatiotemporal Systems
Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations
Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow
Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks
Interpreting Genomic Language Models using Sparse Autoencoders
Interpreting Physics in Video World Models
Intervene When It Doubts: Conjunction-Guided Interactive Reasoning
Interventional Processes For Causal Uncertainty Quantification
In-Training Defenses Against Emergent Misalignment in Language Models
Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal Reasoning
Intrinsic Credit Assignment for Long Horizon Interaction
Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision–Language Models
Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks
Introspection Adapters: Training LLMs to Report Their Learned Behaviors
INT vs. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising
Inverse Depth Scaling From Most Layers Being Similar
Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
Inverting Data Transformations via Diffusion Sampling
Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interaction
Investigating Component Contributions in Multi-Agent ML Systems
Investigating Memory in Model-Free RL with POPGym Arcade
InvGNN: Learning Invertible Node Representations on Graphs
IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient Computation
IPMark: A Sentence-Level Watermark for LLMs with Hierarchical Personalization and Efficient Detection
IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring
IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models
Is Code Better Than Language for Algorithmic Reasoning?
Is Data Shapley Not Better than Random in Data Selection? Ask NASH
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning
Is Generation Required for Data-Efficient Perception?
Is Graph Mixup Beneficial? Investigating Interpolation And Empirical Performance of Graph Mixup Methods
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
Is Spurious Correlation Removal Always Learnable?
Is Task-Specific Training Necessary for Anomaly Detection?
Is the Last Layer Sufficient for Uncertainty Quantification?
Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
Is Your Diffusion Sampler Actually Correct? A Sampler-Centric Evaluation of Discrete Diffusion Language Models
Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives

« prev Page 58/130 next »