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
ALAS: Additive Learnable Alpha-Stable Kernels for Flexible Bayesian Optimization
Alethia: a Foundational Encoder for Voice Deepfakes
Algorithmic Recourse of In-Context Learning for Tabular Data
AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models
AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms
AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
AlignedNorm: Prompting Vision–Language Models via Coupled Prompt Field
Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
Alignment-Aware Decoding
Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories
Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
Alignment Risks from Capability-Seeking RL Training
Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
AlignVid: Taming Visual Dominance via Training-Free Attention Modulation in Text-guided Image-to-Video Generation
Align Your Trajectory Tangent: Training Better Consistency Models via Manifold-Aligned Tangents
AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
A Linearly Convergent Proximal Subgradient Algorithm for Sparse Portfolio Optimization with Transaction Cost
All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
All ERMs Can Fail in Stochastic Convex Optimization Lower Bounds in Linear Dimension
Alleviating Observation Bias via Causal-Invariant Meta-Learning for Unbalanced Incomplete Multi-view Clustering
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
Allocating Variance to Maximize Expectation
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in Unified Multimodal Models via Decompositional Verifiable Reward
AlphaRouter: Token-level Routing Between SLM and LLM with Reinforcement Learning and Tree Search
ALSO: Adversarial Online Strategy Optimization for Social Agents
Alterbute: Editing Intrinsic Attributes of Objects in Images
Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
A Machine-Learned Comorbidity Index
Ambient Dataloops: Generative Models for Dataset Refinement
Ambiguous Strategic Classification
AmbiRefer3D: 3D Visual Grounding with Referential Ambiguity
AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training
A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
A-MemGuard: A Proactive Defense Framework For LLM-Based Agent Memory
A Minimal Agent for Automated Theorem Proving
A Minimax Approach for Optimal Intervention Policy Learning with Two-Stage Outcomes
Amodal Instance Segmentation with IRAIS Dataset for Sim-to-Real Transfer
A model of errors in transformers
Amortized Maximum Inner Product Search with Learned Support Functions
Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation
Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label Disambiguation
Amortizing Maximum Inner Product Search with Learned Support Functions
An Algebraic View of the Expressivity of Recurrent Language Models
AnalogVerifier: A Neuro-Symbolic Framework for Analog Circuit Verification
Analytic Bijections for Smooth and Interpretable Normalizing Flows
An analytic theory of convolutional neural network inverse problems solvers

« prev Page 6/130 next »