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
Blending Neural Control Density Functions for Stabilization and Safety
Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
BLIPs: Bayesian Learned Interatomic Potentials
BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining
BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs
BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking
Blocking the Leakage: Manifold-Aware Gradient Projection for Long-Horizon Test-Time Adaptation
Block Rotation is All You Need for MXFP4 Quantization
Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
BlueCodeAgent: A Blue Teaming Agent Powered by Automated Red Teaming for CodeGen AI
BOCLOAK: Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
BOOSTAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
Boosting CVaR Policy Optimization with Quantile Gradients
Boosting Monocular Metric Depth Estimation via Bokeh Rendering
Boosting World Models Learning via Latent-Space Value Alignment
Boost the Identity-Preserving Embedding for Consistent Visual Generation
Bootstrapped Exploration with Causal Reasoning: A Training Paradigm for Adaptive Forecasting Agent
Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
Bottleneck Communication Delay Minimization for Communication-Efficient Decentralized Learning
Bottleneck-Guided Spectral Subgoals For Offline Goal-Conditioned RL
Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models
Box Thirding: Anytime Best Arm Identification under Insufficient Sampling
BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models
BPL: Generalizable Deepfake Detection via Bias-only Pair-aware Learning
BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language
Brain Networks Should Be Learned, Not Constructed
Branching Diffusion for Point Processes in Time and Space
Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNets
Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners
Breaking Manifold Continuity: Vector Quantized Modeling for Real-Centric Deepfake Detection
Breaking Multi-Task Curse: Reward-Weighted Evolution for Black-Box Many-Task Optimization
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models
Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
Breaking the Computational Barrier: Provably Efficient Actor–Critic for Low-Rank MDPs
Breaking the Echo Chamber: A Dynamic Ensemble Pruning Perspective on MoE
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for Open-Ended LLM Reasoning
Breaking the Factorization Barrier in Diffusion Language Models
Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation
Breaking the Reference Bottleneck via Learning to Rewrite Conversational Queries without Gold Reference Passages
Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge
Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform
Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL
Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning
Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete Time
Brep2Shape: Boundary and Shape Representation Alignment via Self-supervised Transformers
Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching
BRIDGE: Predicting Human Task Completion Time From Model Performance

« prev Page 15/130 next »