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
Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
Temporal Difference Learning for Diffusion Models
Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection
Temporal Preference Optimization for Unsupervised Retrieval
Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future
Temporal Straightening for Latent Planning
Temporal Weighted Encoding: Towards Maximal-Capacity Spike Coding for ANN–SNN Conversion
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
Terminal Dimension Reduction for Time Series with Applications
TerraBind: Fast and Accurate Binding Affinity Prediction through Coarse Structural Representations
TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation
Testing For Distribution Shifts with Conditional Conformal Test Martingales
Test-Time Anchoring for Discrete Diffusion Posterior Sampling
Test-Time Debiasing with Probabilistic Prompts via Wasserstein Distance in Vision-Language Models
Test-Time Detoxification without Training or Learning Anything
Test-time Generalization for Physics through Neural Operator Splitting
Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
Test-Time Guidance for Flow-Based Generative Models via Parallel Tempering on Source Distributions
Test-Time Learning of Causal Structure from Interventional Data
Test-time Offline Reinforcement Learning on Goal-related Experience
Test-Time Reinforcement Learning for Flow Matching
Test-Time Training with KV Binding Is Secretly Linear Attention
TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
TexEditor: Structure-Preserving Text-Driven Texture Editing
TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation
TextAtlas5M: A Large-Scale Dataset for Long Text Image Generation
Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
Text-Conditional JEPA for Learning Semantically Rich Visual Representations
Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space
Text Generation as Continuous Latent Dynamics via Reinforcement Learning
Text Has Curvature
TextME: Bridging Unseen Modalities Through Text Descriptions
TextMesh4D: Zero-shot Text-to-4D Mesh Generation
TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
Textual Stochastic Gradient Descent: Discrete Optimization of External Memory for Reasoning Language Agents
Textual Supervision Enhances Geospatial Representations in Vision-Language Models
TF-FACE: Time-Frequency Fusion Learning via Frequency-Domain Adaptive and Controllable Enhancement for Trajectory Prediction
TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems
TFTF: Training-Free Targeted Flow for Conditional Sampling
T-GINEE: A Tensor-Based Multi-Graph Representation Learning
T-GINEE: A Tensor-Based Multilayer Graph Representation Learning
TGPO: Efficient Policy Optimization through Sequence Anchor and Information Gating
TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains
TGV-KV: Text-Grounded KV Eviction for Vision-Language Models
The Abstraction Gap in Vision-Language Causal Reasoning
The Accumulation of Score Estimation Error in Diffusion Models
The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust
The Appeal and Reality of Recycling LoRAs with Adaptive Merging
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning

« prev Page 113/130 next »