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
Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models
SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis
SVD as a Fast Interpretability Method for Transformers
SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding
SVL: Goal-Conditioned Reinforcement Learning as Survival Learning
SVRG and Beyond via Posterior Correction
SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
SWE-IF: Aligning Code Evaluation with Human Preference
SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution
SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents
SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
SWING: Unlocking Implicit Graph Representations for Graph Random Features
SwitchCraft: A Programmatic Framework for Designing State-Switching Proteins
Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models
Sycophancy Towards Researchers Drives Performative Misalignment
Symbal: Detecting Systematic Misalignments in Model-Generated Captions
Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection
Symbol-Equivariant Recurrent Reasoning Models
SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
Symmetries in language statistics shape the geometry of model representations
Symmetries in PAC-Bayesian Learning
Symmetry in language statistics shapes the geometry of model representations
Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification
SymSpectra: Symmetric Information Bottleneck Framework for Molecular Structure Recognition under Imbalanced Settings
Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization
Synergistic Space-Vision Processing for Predicate Inference
SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment
SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
Syntax vs. Semantics: How Transformers Learn Deep Dependencies
Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors
Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation
Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language
TabICLv2: A Better, Faster, Scalable, and Open Tabular Foundation Model
TabMGP: Martingale Posterior with TabPFN
TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning
TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention
TabularBERT: Binning-Based Self-Supervised Learning for Tabular Representation
TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
Tackling Fake Forgetting through Uncertainty Quantification

« prev Page 111/130 next »