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
CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
Collaborative Disagreement Resolution for Scalable Oversight
Collaborative Learning for Semi-Supervised LiDAR Semantic Segmentation
Collaborative Threshold Watermarking
Collapsed Effective Operators for Higher-order Structures
COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space
Colorful Pinball: Density-Weighted Quantile Regression for Conditional Guarantee of Conformal Prediction
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
Column Thresholding for Sparse Spiked Wigner Models: Improved Signal Strength Requirements
CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models
Combinatorial Sparse PCA Beyond the Spiked Identity Model
CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning
CoMem: Context Management with A Decoupled Long-Context Model
Commit to the Bit: Reactive Reinforcement Learning Done Right
Compact Conformal Subgraphs
Compass-RoPE: Isotropic Rotary Position Embeddings for Vision Transformers
Comp-Attn: Present-and-Align Attention for Compositional Video Generation
Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs
CompleteP for RL: Maintaining Feature Learning When Scaling Deep Reinforcement Learning
Complexity Bounds for Dirichlet Process Slice Samplers
Complexity of Decentralized Optimization with Mixed Affine Constraints
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
Component-Wise Composite Likelihood Distillation for Censored Time-to-Event Data
Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
Compositional Generative Modeling from Decentralized Data
Compositional Planning with Jumpy World Models
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
Compressed Sensing for Capability Localization in Large Language Models
Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter
Computational Arbitrage in AI Model Markets
Computationally-efficient Graph Modeling with Refined Graph Random Features
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Compute Where it Counts: Self Optimizing Language Models
Concept Concentration for Faithful Representation Intervention
Concept-Guided Tokenization: Closing the Gap Between Reconstruction and Generation
Concept Heterogeneity-aware Representation Steering
ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation
Concept Removal for Frontier Image Generative Models
Concept Removal Guidance: Evidence-Calibrated Negative Guidance for Safe Diffusion Sampling
CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control
Conditional Clifford-Steerable CNNs for PDE Modeling
Conditional Coverage Diagnostics for Conformal Prediction
Conditional Diffusion Sampling
Conditional Distributional Treatment Effects: Doubly Robust Estimation and Testing
Conditional Equivalence of DPO and RLHF: Assumptions, Failure Modes, and Provable Alignment
Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment
Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding

« prev Page 21/130 next »