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
Inference-time optimization for experiment-grounded protein ensemble generation
Inference Time Optimization with Confidence Dynamics
INFER: Learning Implicit Neural Frequency Response Fields for Confined Acoustic Environments
InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training
Infinite-Dimensional Generative Diffusions via Doob’s h-Transform
Infinite Mask Diffusion for Few-Step Distillation
Infinite-Precision Autoregressive Modeling for Vector Graphics and Layouts
Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory
Influence-Disentangled Federated Training: Learning Models That Are Easy to Unlearn
Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate
InfoDLM: an Information-Adaptive Framework for Discrete Diffusion Language Model Pretraining
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
InfoGlobe: Local-and-Global Information-Preserving Statistical Manifold Learning for Single-Cell Transcriptomics
InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition
InfoPO: Information-Driven Policy Optimization for User-Centric Agents
Information dynamics and Memory in Neural Networks through Fisher Information Diffusion
Information Flow Reveals When to Trust Language Models
Information-Geometric Adaptive Sampling for Graph Diffusion
Information Geometry Loss for Time Series Forecasting
Information-Theoretic Disentangled Latent Modeling with Conditional Diffusion for Incomplete Multi-View Clustering
Information-Theoretic Generalization Bounds for VAEs: A Role of Encoder and Latent Variable
Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
InfraRL: A Benchmark for Constrained Resource Allocation in Large-Scale Infrastructure Asset Management
InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolution
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
Inner-layer Token Self-modulation as Another Scaling Axis for LLMs
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
Innovation: An Almost Characterization of Hallucination
Insertion Based Sequence Generation with Learnable Order Dynamics
Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers
Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
Instance-Level Costs for Nuanced Classifier Evaluation
Instance-Specific Approximation Ratios for Correlation Clustering and Max-Cut
InstEmb: Instruction-Following Embeddings through Glimpses of the Future
Instruction Decomposition and Action Alignment for Vision-and-Language Navigation
Instruction Decomposition and Action Alignment for Vision-Language Navigation
Instruction Lens Score: Your Instruction Contributes a Powerful Object Hallucination Detector for Multimodal Large Language Models
Integrated Episodic and Semantic Memory via Modulating Transformer FeedForward Layers
Intentional Updates for Streaming Reinforcement Learning
IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning
InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information
InteractComp: Evaluating Search Agents With Ambiguous Queries
Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
Interactive Person Retrieval via Multi-Turn Multimodal Conversation
Interactive Segmentation with Elaborate Focus Prior

« prev Page 57/130 next »