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
Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
Unlearning Isn’t Forgetting: Revealing Hidden Leakage in Class Unlearning Evaluations
Unlearning’s Blind Spots: Over‑Unlearning and Prototypical Relearning Attack
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detection
Unlocking Cross-Modal Biosignal Synthesis: A Temporally-Aware VAE-Diffusion Model
Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models Against Gaussian Noise
Unlocking Speech–Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
Unlocking the Potential of Continual Model Merging: An ODE Perspective
Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards
UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branching
Unpaired Visual Editing with Self-Consistent Flow Matching
Unraveling Syntax: Language Modeling and the Substructure of Grammars
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
Unsat Core Prediction through Polarity-Aware Representation Learning over Clause-Literal Hypergraphs
Unsupervised Camouflaged Object Detection with Dual-Eigenvector Spectral Pseudo-Labeling and Contrastive Refinement
Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching
Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability
Unsupervised Hierarchical Skill Discovery
Unsupervised Neural Langevin Sampler for Mixed Integer Linear Programming
Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
Unsupervised Process-Aware Coreset Selection for In-Context Learning
Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
Unveiling And Addressing Dimensional Collapse In Vector Quantization Models Via Codebook Regularization
Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
Unveiling Prior-Data Fitted Networks on Causal Effect Estimation: Pre-Training or Fine-Tuning?
Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning
Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error Reduction
Unveiling the Role of Data Uncertainty in Tabular Deep Learning
Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs
Unveiling the Visual Counting Bottleneck in Vision-Language Models
UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems
Updating Parametric Knowledge with Context Distillation Retains Post-Training Capabilities
Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations
UrbanMLLM: Joint Learning of Cross-view Imagery for Urban Understanding
URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization
USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning
User-Aware Active Knowledge Acquisition for Emotional Support Dialogue
Use What You Know: Causal Foundation Models with Partial Graphs
Utility Boundary of Dataset Distillation: Scaling and Coverage Laws
Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
Utonia: Toward One Encoder for All Point Clouds
V1: Unifying Generation and Self-Verification for Parallel Reasoners
V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning
Value Aggregation with Uncertainty in Online Decentralized MARL
Value-as-Return: A Two-Stage Framework to Align on the Optimal Score Function
VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models

« prev Page 124/130 next »