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
TriForces: Augmenting Atomistic GNNs for Transferable Representations
Trifuse: Enhancing Attention-Based GUI Grounding via Multimodal Fusion
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios
Tri-Scale Neural ODEs for Continuous Multi-Omics Disease Modeling
TritonGym: A Benchmark for Agentic LLM Workflows in Triton GPU Code Generation
Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
Trust Functions: Near Lossless Weak-to-Strong Generalization by Learning to Trust the Weak Teacher
Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R
Trust-Region Diffusion Policies for Massively Parallel On-Policy RL
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
TrustworthyQENN: A Quantum Evidential Neural Network Based on Complex-Valued Contrastive Learning for Uncertainty Pattern Classification
Truthfulness Does Not Scale Like Reasoning: Why Polling Fails as a Proxy Verifier
TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
TSFAdv: Frequency-Guided Black-Box Adversarial Attacks on Time Series Forecasting
TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
TSMGen: Target-Specific Molecule Generation via Higher-Order Structural Dependencies and Context-Aware Bidirectional Fusion
TSP with Predictions: Heatmap to Tour with Provable Guarantees
TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
TT-Sparse: Learning Sparse Rule Models with Differentiable Truth Tables
Tucker Attention: A generalization of approximate attention mechanisms
TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins
TuneAhead: Predicting Fine-tuning Performance Before Training Begins
Tuning-Free One-Class Discriminant Learning for Tabular Anomaly Detection
Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-Parity
Turbo4DGen: Ultra-Fast Acceleration for 4D Generation
Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers
TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization
TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments
Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization
Tvcache: A Tool-Value Cache for Post-Training LLM Agents
TVDRNet: Text-driven Viewpoint Optimization via Differentiable Rendering for 3D Reasoning Segmentation
TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
Twice Sequential Monte Carlo for Tree Search
TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization
Twins: Learn to Predict Unified Representations with Focal Loss
TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins
TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion Models
Two-dimensional quantization for geometry-aware audio coding
Two-Layer Linear Auto-Regressive Models Estimate Latent States
Two Modalities Are Better Than One: Efficient Adversarial Purification via Multimodal Diffusion Models
Two-Parameter Flows for Learning Population Dynamics of Physical Systems

« prev Page 121/130 next »