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
Calibrating Conservatism for Scalable Oversight
Calibrating Decision Robustness via Inverse Conformal Risk Control
Calibrating Generative Models to Distributional Constraints
Calibrating Uncertainty for Zero-Shot Adversarial CLIP
CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction
CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data
CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling
CalPro: Prior-Aware Evidential Conformal Prediction with Structure-Aware Sensitivity Bounds for Protein Structures
CAMEL: Confidence-Gated Reflection for Reward Modeling
CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping
CamGeo: Sparse Camera-Conditioned Image-to-Video Generation with 3D Geometry Priors
CAMP: Coherent Alignment of Multimodal Prototypes for Explainable Complementary Learning
Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models
Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
CANDI: Hybrid Discrete-Continuous Diffusion Models
Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models
Can Large Language Models Generalize Procedures Across Representations?
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives
Can LLM Agents Stick to the Script? Modeling Commitment in Interactive Narratives
Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
Can LLMs Reason Structurally? Benchmarking via the lens of Data Structures
Can local learning match self-supervised backpropagation?
Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?
Can Muon Fine-tune Adam-Pretrained Models?
Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control
Can Vision Language Models Learn Intuitive Physics from Interaction?
Can VLMs Diagnose and Recover from VLA Manipulation Faults?
Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction
CAOS: Conformal Aggregation of One-Shot Predictors
Capability Traps in DPO
Capacitated Fair-Range Clustering: Hardness and Approximation Algorithms
Capacity-Agnostic Parameter Isolation for Continual Graph Learning
Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization
Capacity without Access: Reinterpreting the Mid-Depth Spectral Plateau in LLMs
CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting
CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation
CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
Caracal: Causal Architecture via Spectral Mixing
CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimation
Cardio-mmFlow: A Gaussian-Prior-Free Physics-Informed Flow Matching Framework for Electrocardiogram to mmWave Radar Synthesis
CARE: Adaptive Calibration for Reliable Recommendations
CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation
CAReDiO: Enhancing Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization
Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features
CAST: Modeling Visual State Transitions for Consistent Video Retrieval
CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments

« prev Page 17/130 next »