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
Spike-HTR: Spiking Neural Transformer for Handwritten Text Recognition
SpikeNet: Sparse Spike-Driven Mask Vector Transformer for Energy-Efficient and Stable Spiking Point Cloud Processing
SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks
SpikingLM: Towards Fully Spiking Language Model
Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
Split Group Knockoffs: Controlling False Discovery Rate in Transformational Group Sparsity
Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
SPLIT-VLM: Salience-Guided Partitioning towards Local Coverage for Importance-Aware Token Dropping in Vision-Language Models
SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis
Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning
SPR: A Structured Prompt Refinement Network for Modality Missing
SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks
SPR-RAFT: Parameter-Efficient Regression-Aware Fine-Tuning for Biomedical LLM Regression
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
Spurious Rewards: Rethinking Training Signals in RLVR
SPUR: Scale-Partitioned Uncertainty Rectification for Robust UAV-on-UAV Interception
S-Quant: Rethinking Weight Quantization with Seed-Based Generation
Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
SSDCN: Spatial-Spectral Dual-Clustering-based Network for Hyperspectral Image Super-resolution
SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models
SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models
Stability Analysis of Sharpness-Aware Minimization
Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Text
Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments
Stabilizing Equation Learning via Zero-Point Constraints
Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls
Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
Stabilizing Native Low-Rank LLM Pretraining
Stabilizing PPO via Latent-Space Regularization and KDE-Driven Exploration
Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
Stabilizing Reinforcement Learning for Diffusion Language Models
Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods
Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
Stable Deep Reinforcement Learning via Isotropic Gaussian Representations
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
StableI2I: Spotting Unintended Changes in Image-to-Image Transition
Stable Localized Conformal Prediction via Transduction
STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics–Physics Dual System
Stable Spectral Copula Alignment for Robust Multimodal Learning
STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems
Stable Velocity: A Variance Perspective on Flow Matching
StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
Stage-wise Distortion–Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
STAND: Self-Aware Precondition Induction for Interactive Task Learning

« prev Page 108/130 next »