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
ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation
Propose, Solve, Verify: Self-Play Through Formal Verification
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning
ProtDBench: A Unified Benchmark of Protein Binder Design and Evaluation
Protein Autoregressive Modeling via Multiscale Structure Generation
Protein Circuit Tracing via Cross-layer Transcoders
Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
Protein Fold Classification at Scale: Benchmarking and Pretraining
Protein Language Model Embeddings Improve Generalization of Implicit Transfer Operators
Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
Proteus: Lookup-Free Trellis-Coded Quantization by Lattice-Breaking Compute Codes for 2-Bit LLMs
ProtocolBench: Which LLM MultiAgent Protocol to Choose?
ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory
Prototype-Based Test-Time Adaptation of Vision-Language Models
Prototype-Grounded Concept Models for Verifiable Concept Alignment
Prototype-guided Bilateral Alignment Multimodal Federated Learning
Prototype Transformer: Towards Language Model Architectures Interpretable by Design
ProtoVAR: Efficient Dataset Distillation via Prototype-Guided Visual Autoregressive Modeling
Provable Accuracy Collapse in Embedding-Based Representations under Dimensionality Mismatch
Provable Accuracy Collapse of Embedding-Based Representations under Dimensionality Mismatch
Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently
Provable Bounds for the Learnability of Sample-Compressible Families from Noisy Samples
Provable Sample Efficiency of Curriculum Post-Training for Transformer Reasoning
Provable Training Data Identification for Large Language Models
Provably Convergent Actor-Critic for MARL through Risk-aversion
Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming
Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function
Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
Provably Label-Efficient Conformal Prediction
Provably Learning Attention with Queries
Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility
Proximal-Based Generative Modeling for Bayesian Inverse Problems
Proximal-IMH: Proximal Posterior Proposals for Independent Metropolis–Hastings with Approximate Operators
Proximal Splitting Methods for Hybrid Differentiable Models
Proxy Compression for Language Modeling
PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation
PSBench: Editing Image via GUI Agents in Photoshop
Pseudo-Mallows for Efficient Probabilistic Preference Learning
PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
PSMix: Robust Point Cloud Recognition through Spectral Domain Mixing
PS-PPO : Prefix-Sampling PPO for Critic-Free RLHF
PsumQuant: In-line Post-training Partial Sum Quantizer for Energy Efficient NPU Inference
pTNAS: Progressive Neural Architecture Search for Tabular Data
Pull Requests as a Training Signal for Repo-Level Code Editing
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification in Language Models

« prev Page 89/130 next »