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
Bayesian Gated Non-Negative Contrastive Learning
Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings
Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurements
Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors
Bayesian Tensor Decomposition with Diffusion Model Prior
Bayes-inspired Integration of Pretrained Priors and Few-Shot Evidence for Few-Shot Classification
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
BEAR: Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis
BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps
(Be Cautious!) Bio-Foundation Models Are Not Yet Robust to Biologically Plausible Perturbations and ML Transformations
BEDTime: A Unified Benchmark for Automatically Describing Time Series
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
Being More Lightweight and Practical: Mini-sized Contrastive Learning Pre-trained Models for Fine-grained Traffic Task
Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
Benchmarking and Enhancing VLM for Compressed Image Understanding
Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
Benchmarking and Improving Fine-Grained Text-to-Image Alignment via Paired Reinforcement Learning
Benchmarking at the Edge of Comprehension
Benchmarking Dense and Indiscernible Object Counting with Blueberries
Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting
Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
Benchmarking the Scientific Mind: A Pathology-Derived Biomedical VQA Benchmark for Complex Scientific Reasoning
Benchmarking World-Model Learning with Environment-Level Queries
Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration
Benign Overfitting in Adversarial Training for Vision Transformers
BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback
BEST: Benchmarking Efficiency in Space and Time for LLM-Generated Code
Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching
Better, Faster: Harnessing Self-Improvement in Large Reasoning Models
Better Training using Weight-Constrained Stochastic Dynamics
Beyond Accuracy and Complexity: The Effective Information Criterion for Structurally Stable Symbolic Regression
Beyond Accuracy: Latent Perturbations for Cognitive-Aware Diagnosis
Beyond Additive Decompositions: Interpretability Through Separability
Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery
Beyond Benchmarks: Toward Causally Faithful Evaluation of Large Language Models
Beyond Binary: Continuous State Optimization with Graph-Structured Objectives
Beyond Blind Noising: Disentangled Visual Rectification for Hallucination Mitigation in MLLMs
Beyond Buffer Limits: Energy-Based Data Reassembly for Continual Learning
Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots
Beyond Correctness: Distance-Based Social Dynamics of Multi-Agent Debate
Beyond Description: Federated Adaptation via Semantic-Visual Prototype Alignment

« prev Page 12/130 next »