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
Fine-Tuning Masked Diffusion for Provable Self-Correction
Fine-Tuning of Transformer models with Frames
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
Fingerprinting Pre-trained Encoders under Arbitrary Downstream Fine-Tuning via Adversarial Shifting
Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets
Finite-time Convergence Analysis of Actor-Critic with Evolving Reward
Finite-Width Neural Tangent Kernels from Feynman Diagrams
FIPN: Forward Self-Organizing Interpretable Polynomial Networks for Time Series Forecasting
FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights
FiRE: Fine-grained Ranking Evaluation for Machine Translation
FIRE: Learning to Navigate and Act on Real-World Files via Stateful Reinforcement Learning
FIRE: Multi-Fidelity Regression with Distribution-Conditioned In-Context Learning Using Tabular Foundation Models
FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection
Fisher-Preserving Guidance: Training-Free Manifold Constraints for Safe Diffusion Control
Fix Before Search: Benchmarking Agentic Visual Query Pre-processing in Multimodal Retrieval-augmented Generation
Fixed Aggregation Features Can Rival GNNs
Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors
FiX: Introducing Fine-grained Forget Gate into Softmax Attention
Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
Fix the Mind, Not the Move: Interpretable AI Assistance via Knowledge-Gap Localization
FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching
FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction
FLARE-AI: Flaw Reporting for AI
FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
FlashOptim: Optimizers for Memory-Efficient Training
FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU
FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs
Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation
FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
Flatland: The Adventures of Gradient Descent with Large Step Sizes
Flat Minima and Generalization: Insights from Stochastic Convex Optimization
Flatness-Aware Stochastic Gradient Langevin Dynamics
Fleet: Few Shots Lead Effective AI-generated Image Detection
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Flexibility-Aware Geometric Latent Diffusion for Full-Atom Peptide Design
Flexible Kernels for Protein Property Prediction
FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble
FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
Float8@2bits: Entropy Coding Enables Data-Free Model Compression
Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations
Flow-Based Density Ratio Estimation for Intractable Distributions with Applications in Genomics
FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
FlowCloud: Learning Continuous Spatiotemporal Dynamics from Unpaired Sparse Point Cloud Snapshots
Flow Equivariant World Models: Structured Memory for Dynamic Environments
Flowers: A Warp Drive for Neural PDE Solvers

« prev Page 43/130 next »