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
A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching
ATLAS: Learning to Optimally Memorize the Context at Test Time
AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Material Structures
Attacking Gray-Box Large Vision-Language Models with Adaptive SVD-Structured Adversarial Alignment
Attacks on Machine-Text Detectors Retain Stylistic Fingerprints
Attend to Anything: Foundation Model for Unified Human Attention Modeling
Attention Hijacking: Backdooring Text Dataset Distillation via Semantic Anchors
Attention Illuminates LLM Reasoning: The Uncovered Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
Attention Implements the Fisher Geometry of Exponential Families
Attention Projection Mixing with Exogenous Anchors
Attention's forward pass and Frank-Wolfe
Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models
Attention Sinks in Diffusion Transformers: A Causal Analysis
Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
Attention with Routed-Memory for Learnable Sparse Control
Attentive Multi-Layer Fusion for Vision Transformers
At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization
Attn-QAT: 4-Bit Attention With Quantization-Aware Training
Attributed Network Alignment: Statistical Limits and Efficient Algorithm
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
A Two-Layer Framework for Joint Online Configuration Selection and Admission Control
A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM Systems
AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion Forcing
AudioMosaic: Contrastive Masked Audio Representation Learning
Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions
AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking
AugServe: Adaptive Request Scheduling for Augmented Large Language Model Inference Serving
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
A Unified Density Operator View of Flow Control and Merging
A Unified Framework for Deep Hypergraph Clustering Beyond Homophily
A Unified Framework for Diffusion Model Unlearning with f-Divergence
A Unified Sparse Attention via Multi-Granularity Compression
A unified theory of feature learning in RNNs and DNNs
A Unifying Relational Perspective on Expressive Lottery Tickets
A Unifying View of Variational Generative Wasserstein Flows
AURA: Visually Interpretable Affective Understanding via Robust Archetypes
AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning
AutoBaxBuilder: Bootstrapping Code Security Benchmarking
Autobidding Auctions with LLM-Powered Creatives
AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning
Automated Formal Proofs of Combinatorial Identities via Wilf–Zeilberger Guidance and LLMs
Automatically Finding Reward Model Biases
Automatic Construction of Clinical Scoring Systems with LLM Agents
Automatic Layer Selection for Hallucination Detection
Automatic Pruning Discovery for Large Language Models
Automatic Unsupervised Ensemble Outlier Model Selection
AutoMat: Physics-Guided Agentic Reasoning for Solving Ill-Posed Inverse Microscopy Problems
AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture -of-Transformers for End-to-End Autonomous Driving

« prev Page 10/130 next »