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
DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation
DisPPO: Quantile-Based Distributional Reinforcement Learning for Large Language Models
Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection
Dissecting Causal Mechanism Shifts via FANS: Function And Noise Separation
Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers
Dissecting Post-Training: Uncovering the Complementary Roles of SFT and RL for Document Parsing
Dissecting Quantization Error: A Concentration-Alignment Perspective
Dissecting the Safety Circuit: Neuronal Intervention for Transferable Adversarial Attacks on VLMs
DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction
DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training
Distillation Models are Good Samplers for Diffusion Reinforcement Learning
Distilling Linearized Behavior into Non-linear Fine-Tuning for Effective Task Arithmetic
Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs
Distilling Task-Level Coordination Policies for Generalizable Multi-Agent Cooperation
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
Distinguishing Imitation Error from Intrinsic Motion Learning Difficulty
DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction
Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner
Distributed Direct Preference Optimization
Distributed Stochastic $K$-Level Optimization Over Networks
Distributional Active Inference
Distributional Alignment Games for Answer-Level Fine-Tuning
Distribution Alignment for One-Shot Federated Learning via Optimal Transport
Distributional Inverse Reinforcement Learning
Distributionally Robust Causal Abstractions
Distributionally Robust Markov Games with Average Reward
Distributionally Robust Reinforcement Learning from Human Feedback
Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-Judge
Distribution Matching Variational AutoEncoder
Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation
DITING: A Weak Degradation Listener for Battery Lifetime Early Prediction
DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs
DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation
DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery
Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
Diversity-Aware Recursive Feature Multiple Kernel Learning
Diversity-aware Weight Perturbation Promotes Robust Adaptation
Diversity-Driven Offline Multi-Objective Optimization via Nested Pareto Set Learning
Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models
Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake Detection
Divide and Contrast: Learning Robust Temporal Features without Augmentation
Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models
Divide and Learn: Multi-Objective Combinatorial Optimization at Scale
Diving into Kronecker Adapters: Component Design Matters

« prev Page 31/130 next »