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
Full-Spectrum Graph Neural Networks: Expressive and Scalable
FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation
Fully Dynamic Coreset Spectral Clustering
Fully Zero-Shot Image Dehazing
FunCQNet: A Functional Censored Quantile Neural Network for Predicting Long-Term Post-Transplant Kidney Survival
Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces
Functional Attention: From Pairwise Affinities to Functional Correspondences
Functional building blocks of neural networks: from network motifs to collective dynamics
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
Functional Decomposition and Shapley Interactions for Interpreting Survival Models
Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity
Function-Valued Causal Influence in Nonlinear Time Series
FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds
Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
FUSE: Ensembling Verifiers with Zero Labeled Data
FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation
FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification
FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing
FUSE: Full‑spectrum Unlearnable Examples via Spectral Equalization
FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty
FusionCell: Cross-Attentive Fusion of Layout Geometry and Netlist Topology for Standard-Cell Performance Prediction
Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion
Future Dynamic 3D Reconstruction: Toward 3D World Modeling with Disentangled Ego-Motion
Future-Gain Guided Test-Time Learning for Large Language Models
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
G$^2$RPO: Geometric GRPO Escaping LLMs' Reasoning Ruts to Break the Accuracy--Entropy Trade-off
G$^2$RPO: Geometric GRPO; Escaping LLM's Reasoning Rut to Break Accuracy--Entropy Trade-off
G$^2$TAM: Geometry Grounded Track Anything Model
G2RPO: Geometric GRPO; Escaping LLM's Reasoning Rut to Break Accuracy--Entropy Trade-off
GAAVI: Global Asymptotic Anytime Valid Inference for the Conditional Mean Function
GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert
GameDevBench: Evaluating Agentic Capabilities Through Game Development
Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery
GameVerse: Can Vision-Language Models Learn from Video-based Reflection?
Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking
GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
Gateways to Tractability for Satisfiability in Pearl’s Causal Hierarchy
Gauge-Equivariant Graph Networks via Self-Interference Cancellation
GAUSS: Graph-Assisted Uncertainty Quantification using Structure and Semantics for Long-Form Generation in LLMs
Gaussian Mean Field Variational Inference can Overestimate Predictive Variance
GaussTrace: Provenance Analysis of 3D Gaussian Splatting Models with Evidence-based LLM Reasoning
GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls
GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth
GEM-FI: Gated Evidential Mixtures with Fisher Modulation
GEM: Geometric Entropy Mixing for Optimal LLM Data Curation

« prev Page 47/130 next »