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
Glimpse: Geometry Learning of Multi-scale Structural Priors for 3D Pose Estimation
Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
Global Credit Assignment via Dynamical Criticality
Global Directional Priors with Local Statistical Validation for Scalable Causal Discovery
Global Geometry Is Not Enough for Vision Representations
Global Merger-Arbitrage Forecasting with Language Models
Global Plane Waves from Local Gaussians: Periodic Charge Densities in a Blink
Global Policy-Space Response Oracles for Two-Player Zero-Sum Games
Goal-Conditioned Agents that Learn Everything All at Once
Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimization
GOCM: Single-Step Graph Outlier Synthesis via Origin Consistency Model
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific Signatures
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction
GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data
GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks
gp2Scale: A Class of Compactly Supported Non-Stationary Kernels and Distributed Computing for Exact Gaussian Processes on 10 Million Data Points
GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models
Gradient-Aware Scheduling: Coupling Curriculum and Staleness for Async Reinforcement Learning
Gradient-Based Causal Tree Ensembles: A Backbone Architecture for Heterogeneous Treatment Effects
Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration
Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway
Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization
Gradient Flow Sampler-based Distributionally Robust Optimization
Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions
Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity
Gradient Inversion Attacks Beyond SGD
Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation
Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization
GradientStabilizer: Fix the Norm, Not the Gradient
Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Model
Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models
Gradient Testing and Estimation by Comparisons
Gradient Transformer: Learning to Generate Updates for LLMs
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent
GradPower: Powering Gradients for Faster Language Model Pre-Training
Gram2Token: Enabling Run-time GPU-Native Grammar-Constrained Decoding for LLMs
G-RANS: Generalizable Residual-Aware Neural Solvers for Sparse Systems
Granularity-Aware Adaptive Classifier Expansion via Zero-Shot Learning
GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval
Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings
Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
GraphFLEx: Unsupervised Structure Learning $\underline{\text{F}}$ramework for $\underline{\text{L}}$arge $\underline{\text{Ex}}$panding $\underline{\text{Graph}}$s
GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving
Graph-GRPO: Training Graph Flow Models with Reinforcement Learning
Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
Graph is a Substrate Across Data Modalities
Graph-Link: Bridging the Semantic-Structural Gap in Text-to-SQL via Constrained Subgraph Induction

« prev Page 50/130 next »