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
ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic Education
Clipped Q-Learning: Your Value Clipping Is Secretly A Robust Operator
Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals
Clipping Low-Probability Tokens in SFT Yields a Generalizable Initialization for RL
Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers
CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large Vision-Language Models
Closing the Expression Gap in LLM Instructions via Socratic Questioning
Closing the Loop: Universal Repository Representation with RPG-Encoder
Closing the Sim-to-Real Gap in Network Spreading Processes via GPU-Accelerated Distributional RL
Closing the Sim-to-Real Gap in Non-Markovian Spreading Processes via GPU-Accelerated Distributional RL
CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings
[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series
Clustered Influence Functions
Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning
Clustering in Deep Stochastic Transformers
CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction
cMoLLM at Scale: Horizontal Scaling Laws for Convolutionally-Gated Mixture-of-LLMs
Coarse-Grained Boltzmann Generators
COBRA: Contribution-Based Bayesian Rank Allocation for Parameter-Efficient Fine-Tuning
CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement Learning
CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
CoCoQuant: Breaking the Bandwidth Wall via Co-Optimized Communication and Computation Quantization
CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers
CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning
CoDA-Bench: Can Code Agents Handle Data-Intensive Tasks?
Code2Video: A Code-centric Paradigm for Educational Video Creation
Code2Worlds: Empowering Coding LLMs for 4D World Generation
CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer
CodeClash: Benchmarking Goal-Oriented Software Engineering
CodeMamba: Shifting from Target Semantics to Self-Supervised Background Manifold Learning for Singularity Detection in Infrared Sequences
CodeTaste: Can LLMs Generate Human-Level Code Refactorings?
CODiff: One-Step Diffusion Model for Camouflaged Object Detection
CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
CoEvol-NO: State and Coordinate Co-Evolution with an Error-Driven Predictor-Corrector Paradigm for Neural Operator Transformer
Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
Co-Evolving Latent Action World Models
CofactGVR: Counterfactual Intervention for Grounded Visual Reasoning
CoFrGeNet: Continued Fraction Architectures for Language Generation
CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation
COFT: Counterfactual–Conformal Decoding for Fair Chain‑of‑Thought Reasoning in Large Language Models
CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization
CoGenCast: A Coupled Autoregressive–Flow Generative Framework for Time Series Forecasting
Co-Generative De Novo Functional Protein Design
CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detection
Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing
CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
Cold-Start Personalization via Bayesian Adaptive Questioning

« prev Page 20/130 next »