ICLR 2026

5,370 papers

Top Research Directions

Research directions most represented by ICLR 2026 papers.

Scaling Language Model Reasoning Beyond Verifiable Rewards 88
Group Relative Policy Optimization for Large Reasoning Models 81
General Purpose Reasoning from Specialized Reinforcement Learning 79
Shifting from Static Benchmarks to Dynamic Evaluation 66
The Decoupling of Visual Perception and Logical Reasoning 51
Mitigating the Inference Latency of Chain of Thought 50
Activation Steering for Inference Time Model Control 41
Preventing Entropy Collapse in Reinforcement Learning 41
Inference Time Compute Scaling for Complex Reasoning 38
Reinforcement Learning with Verifiable Rewards 38
Autonomous Code Refinement via Execution Feedback Loops 38
Mitigating Computational Overthinking in Large Reasoning Models 37
Resolving Superposition with Sparse Autoencoders 34
Role Specialization in Multi-Agent Architectures 34
The Spatial Reasoning Bottleneck in Multimodal Models 33

Top Authors

AuthorPapers
Fei Huang20
Ge Zhang19
Jianye HAO19
Dahua Lin17
Junchi Yan17
Michael M. Bronstein17
Yejin Choi17
James Y. Zou16
James Zou16
Bo Han15
Jingren Zhou15
Min Zhang15
Tat-Seng Chua15
Caiming Xiong14
Dawn Song14
Pengfei Wan14
Yi Yang14
Jiaheng Liu13
Kai Chen13
Pengjun Xie13

Impactful Papers

Papers from ICLR 2026 that shaped research clusters.

Foundational

Papers

Title
Diffusion Bridge Variational Inference for Deep Gaussian Processes
Diffusion-DFL: Decision-focused Diffusion Models for Stochastic Optimization
Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function
Diffusion Language Model Knows the Answer Before It Decodes
Diffusion Language Models are Provably Optimal Parallel Samplers
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Diffusion Models as Dataset Distillation Priors
Diffusion Negative Preference Optimization Made Simple
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
Diffusion Transformers with Representation Autoencoders
DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing
DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
Dimension-Free Decision Calibration for Nonlinear Loss Functions
DiMeR: Disentangled Mesh Reconstruction Model with Normal-only Geometry Training
Direct Doubly Robust Estimation of Conditional Quantile Contrasts
Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding
Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs
Directional Textual Inversion for Personalized Text-to-Image Generation
Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach
Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild
DirMoE: Dirichlet-Routed Mixture of Experts
Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement
Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring
DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
Discounted Online Convex Optimization: Uniform Regret Across a Continuous Interval
Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces
Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
Discovering and Steering Interpretable Concepts in Large Generative Music Models
Discovering heterogeneous synaptic plasticity rules via large-scale neural evolution
Discovering Novel LLM Experts via Task-Capability Coevolution
DiscoX: Benchmarking Discourse-Level Translation in Expert Domains
Discrete Adjoint Matching
Discrete Bayesian Sample Inference for Graph Generation
Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning
Discrete Diffusion for Bundle Construction
Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
Discrete Diffusion Trajectory Alignment via Stepwise Decomposition
Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
Discrete Latent Features Ablate Adversarial Attack: A Robust Prompt Tuning Framework for VLMs
Discrete Variational Autoencoding via Policy Search
Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
Disentangled Representation Learning for Parametric Partial Differential Equations
Disentangled representation learning through unsupervised symmetry group discovery
Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
Disentanglement of Variations with Multimodal Generative Modeling
Disentangling Knowledge Representations for Large Language Model Editing
Disentangling Length Bias in Preference Learning via Response-Conditioned Modeling
Disentangling the Factors of Convergence between Brains and DINOv3
DISK: Differentiable Sparse Kernel Complex for Efficient Spatially-Variant Convolution

« prev Page 24/108 next »