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
ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
SC-FAGC: Size Constrained Fast Anchor-based Graph Clustering
Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions
Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models
SCHUR-A*: Layer-wise Optimal Expert Pruning for MoEs via Schur-Complement Guided A* Search
SciAgentGym: Benchmarking Multi-Step Scientific Tool-Use in LLM Agents
Scientific logicality enriched methodology for LLM reasoning: A practice in physics
SciNet: Evaluating AI Agents in Relation-Aware Scientific Literature Retrieval
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models
SCNS: Continual Personalization of Diffusion Models via Submodular Concept Neuron Selection
SCoA: Revisiting Domain Generalized Object Detection with Style-Conditioned Adaptation
SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments
SCOPE: Selective Conformal Optimized Pairwise LLM Judging
SCORE: A Unified Framework for Overshoot Refund in Online FDR Control
Score Based Error Correcting Code Decoder
Score Correction for Generative Models with Probabilistic Constraints
ScoreMatchingRiesz: Score Matching for Debiased Machine Learning and Policy Path Estimation
ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition
Score-Repellent Monte Carlo: Toward Efficient Non-Markovian Sampler with Constant Memory in General State Spaces
SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference
SCOUT: Cyclic Causal Discovery Under Soft Interventions with Unknown Targets
ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision
SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation
SDiD:Shared diffusion prior for efficient distributed stereo image compression
SDiD: Shared Diffusion Prior for Efficient Distribute Stereo Image Compression
SD-MoE: Spectral Decomposition for Effective Expert Specialization
SE(3)-Equivariant Flow Matching with Gaussian Process Priors for Geometric Trajectory Prediction
SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
Search Space Synthesis for Parametric Functions
SecCodePRM: A Process Reward Model for Code Security
Second-Order Bilevel Optimization with Accelerated Convergence Rates
Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
Secure Multi-agent Reinforcement Learning for Service Systems with Affinity and Byzantine Nodes: Stability Analysis and Protection Design
Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
Securing Multimodal AI through Internal Information Decomposition
Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense
SEDRAS: Symbolically Evaluated Deep Research And Science
See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent
See First, Reason Later: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
Seeing is Solving: Unlocking Efficient Multimodal RL via View Alignment
Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs
Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
Seeing Symbols, Missing Structure: A Real-World Handwritten Mathematical Expression Recognition Benchmark for Large Models

« prev Page 101/130 next »