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
Facts in Stats: Impacts of Pretraining Diversity on Language Model Generalization
FAFO: Lossy KV Cache Compression for Lossless Inference Acceleration via Draftless Fumble Decoding
FAIL: Flow Matching Adversarial Imitation Learning for Image Generation
Failure-Driven Workflow Refinement
Failure is Feedback: History-Aware Backtracking for Agentic Traversal in Multimodal Graphs
FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models
Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off
Fair Dataset Distillation via Cross-Group Barycenter Alignment
Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency
Fair-FedMOE: Group-Fair One-Shot Federated Learning via Prototype-Guided Experts for Medical Imaging Analysis
FairGB: A Fair Granular-Ball Generation Method for Data Classification
FairJudge : An Adaptive, Debiased, and Consistent LLM-as-a-Judge
FairMerging: Rethinking Model Merging through the Lens of Fairness
Fairness in Aggregation: Optimal Top-$k$ and Improved Full Ranking
FairRARI: A Plug and Play Framework for Fairness-Aware PageRank
FairSSL: Fair Multimodal Self-Supervised Learning
Fair Transit Stop Placement: A Clustering Perspective and Beyond
Faithful Mobile GUI Agents with Guided Advantage Estimator
Faithful Relational Reasoning with Region-based Embeddings: Expressivity of Convex Coordinate-wise Models
FakeWorld 1.0: An Omni-modal Benchmark for Fake Media and Content
Falling Trees: A Model Class for Interpretable Risk Prioritization
Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
FaPS: A General and Fast Training Method for Diffusion Models
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits
Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning
Fast and Near-Optimal Algorithms for Private Hypothesis Selection
Fast and Scalable Analytical Diffusion
FAST-AR: Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention
Fast Byte Latent Transformer
Faster Activation Functions at the Edge for Post-Training Speedups
Faster Query-Key Learning Sharpens Attention in Self-Attention Models
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
Fast Estimation for Forest Matrix of Signed Graphs
Fast kernel methods: Sobolev, physics-informed, and additive models
Fast k-means Seeding Under The Manifold Hypothesis
Fast KV Compaction via Attention Matching
Fast Mixing Steady-State Control in Markov Decision Processes
Fast Mixture of Curvature-Aware Experts for Diverse and Dynamic Graph Topologies
Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding
Fast Reconstruction of Mixtures of Bernoulli Product Distributions
Fast-SAM3D: 3Dfy Anything in Images but Faster
FastSESR: Fast Scene-level Explicit Surface Reconstruction
Fast Spectrally Sparse Signal Reconstruction via Jacobi-Preconditioned Gradient Descent
Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving
Feasible Fusion: Constrained Joint Estimation under Structural Non-Overlap
Feature-Aware (Hyper)graph Generation via Next-Scale Prediction
Feature Bagging Provides Stability
Feature Collapse Under Corruption: An Entropy Perspective on Robust Neural Networks

« prev Page 41/130 next »