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
Flow for Future: Geometric SE(3)-Equivariant Flow Matching for 3D Trajectory Prediction
FlowMAP: Flow Matching for Generalizable Agent Planning
Flow Matching Calibration for Simulation-Based Inference under Model Misspecification
FlowNar: Scalable Streaming Narration for Long-Form Videos
FlowPET: Physics-Informed Symplectic Flow Matching for Low-Count PET Reconstruction
Flow Sampling : Learning to Sample from Unnormalized Densities via Denoising Conditional Processes
FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation
FlowState: Sampling-Rate‑Equivariant Time‑Series Forecasting
FluxNet: Learning Capacity-Constrained Local Transport Operators for Conservative and Bounded PDE Surrogates
FOAM: Blocked State Folding for Memory-Efficient LLM Training
FOAM: Frequency and Operator-Error Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation
FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy
Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detection
Focus and Dilution: The Multi-stage Learning Process of Attention
FOCUS: DLLMs Know How to Tame Their Compute Bound
FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization
Focusing: View-Consistent Sparse Voxels for Efficient 3D VAE Training
Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain
FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance For Pruned Large Language Models
Focus-Then-Contact: Speeding Up Robotic Contact-Rich Task Learning with Affordance-Guided Real-World Residual Reinforcement Learning
FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models
Foreground-Aware Token Routing Vision Transformer for Real-Time Satellite Video Tracking
ForensicConcept: Transferable Forensic Concepts for AIGI Detection
Forensic Prompting with Dual-Action Policy Optimization for Vision-Language Forgery Detection and Localization
Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks
Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
Forgetting Whenever You Want: A Decentralized Continual Learning Framework with On-Demand Unlearning
Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models
FormAct: Agentic Source Editing for Rich-Format Document Generation
Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning
Formalizing and Falsifying Causal Pathways of Rare Events
Formalizing Learning from Language Feedback with Provable Guarantees
Formalizing the Binding Problem
FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
Formally Exploring Visual Anomaly Detection Evaluation Metrics
FormalRx: Rectify and eXamine Semantic Failures in Autoformalization
FormulaCode: Evaluating Agentic Optimization on Large Codebases
Forward-Chaining Temporal Point Process
Forward-KL Convergence of Time-Inhomogeneous Langevin Diffusions
Foundation Inference Models for Ordinary Differential Equations
Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
Foundation VAE for CT Reconstruction, Augmentation, and Generation
Foundation VAEs for CT Reconstruction, Augmentation, and Generation
FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
Fourier Features Let Agents Learn High Precision Policies with Imitation Learning

« prev Page 44/130 next »