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
Robustness of Mixtures of Experts to Feature Noise
Robust Parallel Diffusion Sampling via Dynamic Jacobian Bandwidth
Robust Self-reflective Hashing for Cross-modal Retrieval with Noisy Label
Robust Sequential Experimental Design for A/B Testing
Robust Signal Enhancement via Fractional Detail Views and Knowledge Guided Multi-view Fusion
Robust Stochastic Gradient Posterior Sampling with Lattice Based Discretisation
Robust Strategic Classification under Decision-Dependent Cost Uncertainty
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
Robust Vision-Language Models via Manifold-Adversarial Adapters
RoCA: Robust Cross-Domain End-to-End Autonomous Driving
Role-Level Inductive Bias for Cross-Task Generalization in Multi-Agent Reinforcement Learning
Romberg-Extrapolated Zeroth-Order Gradient Estimator: Higher-Order Bias Reduction with Preserved Leading Directional Variance
Root Cause Analysis of Failures in Microservices via Bayesian Root Cause Discovery
Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
Rotary Position Encodings for Graphs
Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
Routing and Reasoned Evaluation with Large Language Models
Routing by Reaching: Composition of Pre-trained GFlowNets for Multi-Objective Generation
Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression
RSA-CP: Efficient Conformal Prediction in Small-Sample Regimes via Random Score Alignment
RSAgent: Learning to Reason and Act via Multi-Turn Tool Invocations for Text-Guided Segmentation
RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation
RSPO: Regularized Self-Play Alignment of Large Language Models
RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers
RTInfer: Real-Time Inference of Multiple DNNs on Edge GPUs
RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference
Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
RubricRobustness: Evaluating the Sensitivity of Rubrics-Based Benchmarks to Simple Perturbations
RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation
RulePlanner: All-in-One Reinforcement Learner for Unifying Design Rules in 3D Floorplanning
RVAS: Referring Video Active Exploration and Segmentation
S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction
S2M-Net: Spectral-Spatial Mixing with Morphology-Aware Adaptive Loss for Medical Image Segmentation
SABER: Continual Learning with Representation Conflict Management
SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning
SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
SAEs-BrainMap: Unveiling the Emergence of Specialized Concepts in Deep Models via Brain Alignment
Safe and Scalable Web Agent Learning via Recreated Websites
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
SafeCompass: Dynamic Chain-of-Thought Steering via Inference-Time Safety Signals
SafeDec: Constrained Decoding for Safe Autoregressive Generalist Robot Navigation Policies
Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

« prev Page 98/130 next »