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
Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation
Iterated Population Based Training with Task-Agnostic Restarts
Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
Iterative Robust Satisficing: Minimizing Performance Degradation Under Distribution Shift
iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
ITSPACE: Monotone Gaussian Optimal Transport Updates
It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks
iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning
IVQA-LD: Inclusive Multimodal Understanding for Population with Limb Deficiency
IVQ: Structured and Lightweight Vector Quantization via Binary Hierarchical Composition Inspired by $\textit{IChing}$
iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference
JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG
JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks
JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
Jailbreaking Vision-Language Models Through the Visual Modality
Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
JANUS-LORA: A Balanced Low-Rank Adaptation for Continual Learning
JanusPipe: Efficient Pipeline Parallel Training for Machine Learning Interatomic Potentials
Joint-Embedding Predictive Learning of Latent Market States in U.S. Equities
Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits
Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution
Joint Learning in the Gaussian Single Index Model
Joint Model and Data Sparsification via the Marginal Likelihood
Joint Navigation and Manipulation Planning with 3D Interaction Chains
Joint-Space Empowerment as a Theory of Dexterous Motor Coordination
Joint-Space Empowerment for Dexterous Coordination in Tendon-Driven Hands
Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math
Judgment Operators: A Composition-Invariant Substrate for Multi-Agent Action Spaces
Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
Just Noticeable Difference Modeling for Deep Visual Features
Just Y-Prediction: Enabling Historical Cumulative Inconsistency in Label Diffusion for Learning with Noisy Label
Just Y-Prediction: Enabling Historical Cumulative Inconsistency in Label Diffusion for Learning with Noisy Labels
KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning
Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modeling and State Tracking
KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies
Keeping a Secret Requires a Good Memory: Unconditional Streaming Lower-Bounds for Differentially Private Algorithms
Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams
KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits
Kernel-based Maximum-of-difference Test for Two-sample Comparison
KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware
KernelFoundry: Hardware-Aware Evolutionary GPU Kernel Optimization
KineFlow: Kinematic Second-Order Flow Matching for Time-Series Forecasting
Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes

« prev Page 59/130 next »