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
Time Series Forecasting Through the Lens of Dynamics
Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
Time series saliency maps: Explaining models across multiple domains
Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces
TimeSpot: Benchmarking Geo-Temporal Understanding in Vision–Language Models in Real-World Settings
Timestep Rescheduling in Diffusion Inversion
TIME: Tensor-Factorized Mixture-of-Experts with Intrinsic Routing for Lifelong Multimodal Knowledge Editing
TiME: Test-Time Mixture-of-Experts Routing via Asymmetric CO-Optimal Transport for Continual Test-Time Adaptation
TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts
TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs
Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts
TMD-Bench: A Multi-Level Evaluation Paradigm for Music–Dance Co-Generation
T-measure: A Topology-Consistent Metric for Binary Segmentation
TMS: Trajectory-Mixed Supervision for On-Policy Self Distillation
TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
ToaSt: Token Channel Selection and Structured Pruning for Efficient ViT
TodoEvolve: Learning to Architect Agent Planning Systems
To Grok Grokking: Provable Grokking in Ridge Regression
TokenDrop: Token-Level Importance-Aware Backward Propagation Skipping for Efficient LLM Fine-Tuning
Token-Efficient Change Detection in LLM APIs
Token-Free Hierarchical Indexing for RAG beyond LLM-based Summarization
Tokenised Flow Matching for Hierarchical Simulation Based Inference
Token-Level LLM Collaboration via FusionRoute
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
Token Sample Complexity of Attention
Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning
TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models
TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind
TOM-SWE: User Mental Modeling For Software Engineering Agents
Tool-Framing Bypasses LLM Safety: Procedural Abstraction Reduces Refusal Rates by Up to 40 Percentage Points Across Models
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
TopAdapter: Topology-Aware Prompt Tuning for Efficient Point Cloud Understanding
TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering
TopoDistill: Distilling Global System Topology for Causal Discovery in Multivariate Time Series
Topological Active Inference for Task Disambiguation
Topology-Aware Contrastive Learning: Regulating Representation Connectivity via Persistent Homology
Topology-Preserving Neural Operator Learning via Hodge Decomposition
Torus Graphs for Large Scale Neural Phase Analysis
Tournament Style RL: Stabilizing Policy Optimization on Non Verifiable Problems
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
Toward Cybersecurity-Expert Small Language Models
Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach
Toward Identifiable Sparse Autoencoders
Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages
Towards Achieving Optimal Strong Regret and Constraint Violation via Computationally Efficient Model-free RL
Toward Safe Quantization-Aware Fine-tuning: Understanding and Mitigating Safety Alignment Degradation

« prev Page 117/130 next »