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
Large Language Models as Topological Thinkers: A Benchmark on Graph Persistent Homology
Large Language Models Develop Novel Social Biases Through Adaptive Exploration
Large Language Models Explore by Latent Distilling
Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
Large Scale Manifold Balanced Clustering
Large-Scale Molecular Dynamics Simulation: Direct Interatomic Modeling with Dilated Message Passing
Large-Scale Molecular Dynamics Simulations: Direct Interatomic Modeling with Dilated Message Passing
Large-Scale Notification Dispatch with Bundle Treatments and Multi-Outcome Uplift Optimization
Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments
Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
Large Vision-Language Models Get Lost in Attention
LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning
LASER: Learning Active Sensing for Continuum Field Reconstruction
LassoFlexNet: a Flexible Neural Architecture for Tabular Data
LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment
Last-iterate Convergence of ADMM on Multi-affine Quadratic Equality Constrained Problem
Last-Iterate Convergence of Regularized Gradient Methods for Stochastic Monotone Variational Inequalities
LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
Latent Collaboration in Multi-Agent Systems
Latent Diffusion Pretraining for Crystal Property Prediction
Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
Latent-Guided Cooperative Energy-Based Models
Latent Guided Sampling for Combinatorial Optimization
Latent Laplace Diffusion for Irregular Multivariate Time Series
LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering
Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning
Latent Space Robust Optimization of Neural Processes with Aligned Stratified Order-Statistic Loss Reduction
Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer
LAVA: A Unified Framework for Finetuning Language and Vision Models
Lavida-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
Layer-Centric Factors of Variation Disentanglement for Task- and Model-Agnostic Generalization
LayerT2V: A Unified Multi-Layer Video Generation Framework
Layer-wise Gradient Disentanglement: Decoupling Semantics and Preferences in Direct Preference Optimization
LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding
LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
L-CUBE: Isolating Long-Context Capacity from Knowledge with Controllable Mutual Information Scaling
LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling
L-Drive: Beyond a Single Mapping—Latent Context Drives Time Series Forecasting
Leaderboard Incentives: Model Rankings under Strategic Post-Training
Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
LeakGFN: Robust Molecular Generation in Generative Flow Networks via Flow Decomposition
LEAP: Zone-Aware MCTS for LLM Self-Speculative Decoding

« prev Page 61/130 next »