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
Private and Stable Test-time Adaptation with Differential Privacy
Private Learning with Public Feature Conditioning
Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data
PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees
PrivGate: Steering Contextual Integrity in LLMs via Latent Space Geometry
Privileged Information Distillation for Language Models
PRM-PBE: Process Reward Model for Reinforcement Learning in Programming-by-Example
ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response
Proactive Defense Benchmark against Deepfake Generation
ProactiveLLM: Learning Active Interaction for Streaming Large Language Models
Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
Probabilistically-routed Bayesian Additive Spanning Trees for Learning on Constrained Domains
Probabilistic Bisection Algorithm Provably Achieves Exponential Convergence
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
Probabilistic Retrofitting of Learned Simulators
Probabilistic Robustness Certificates against Adversarial Attacks
Probabilistic Salient Object Ranking
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
Probability of Matching for Batch Multi-Objective Bayesian Optimization
Probably Approximately Correct Labels
ProbeLLM: Automating Principled Diagnosis of LLM Failures
Probing Cross-modal Information Hubs in Audio-Visual LLMs
Probing How Scalable Table Data Enhances General Long-Context Reasoning
Probing RLVR Training Instability through the Lens of Objective-Level Hacking
Probing the Geometry of Diffusion Models with the String Method
Probing the Inductive Bias of Neural Networks through Learning Random Cellular Automata
Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction
Problem Distributions as Tasks: Repurposing Meta Learning for Generative Combinatorial Optimization towards Multi-task Pretraining and Adaptation
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
Procedural Generation Of Algorithm Discovery Tasks in Machine Learning
Procedural Pretraining: Warming Up Language Models with Abstract Data
Process Reward Agents for Steering Knowledge-Intensive Reasoning
ProConMV: Provenance-Enabled Conceptual Framework for Interpretable Multi-View Diabetic Retinopathy Diagnosis
ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation
Profiling the Irrational Agent: Cognitive Modeling of LLM Behaviors in Sequential Jailbreaks
Progressive Cramming: Reliable Token Compression and What It Reveals
Progressive Graph Structure Adjustment for Homophily Shift Adaptation
Projection-Free Algorithms for Minimax Problems
ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression
ProMeCD: Unifying Long-Tailed and Noisy Label Learning via White-Box Control
ProMiSE: Protein Multi-State Evaluation Benchmark in Biological Contexts
PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs
Prompt Injection as Role Confusion
Prompt Optimization with Minimal Unlabeled Input via Meta-Reasoning
PromptPilot: Game-Theoretic Multi-Agent Prompt Optimization for Segment Anything
Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers
PromptRL: Prompt Matters in RL for Flow-Based Image Generation
Prompt Tuning for CLIP on the Pretrained Manifold
ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modeling

« prev Page 88/130 next »