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
Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model
AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception
AnyUp: Universal Feature Upsampling
APC-RL: Exceeding data-driven behavior priors with adaptive policy composition
A Physics-Inspired Optimizer: Velocity Regularized Adam
AP-OOD: Attention Pooling for Out-of- Distribution Detection
APPLE: Toward General Active Perception via Reinforcement Learning
A Primer on SO(3) Action Representations in Deep Reinforcement Learning
A Probabilistic Hard Concept Bottleneck for Steerable Generative Models
A Problem-Oriented Perspective and Anchor Verification for Code Optimization
APT: Towards Universal Scene Graph Generation via Plug-in Adaptive Prompt Tuning
AQER: A Scalable and Efficient Data Loader for Digital Quantum Computers
AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions
Arbitrary Generative Video Interpolation
Arbitrary-Order Block SignSGD for Memory-Efficient LLM Fine-Tuning
Arbitrary-Shaped Image Generation via Spherical Neural Field Diffusion
Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment
A Recovery Guarantee for Sparse Neural Networks
Are Deep Speech Denoising Models Robust to Adversarial Noise?
Are EEG Foundation Models Worth It? Comparative Evaluation with Traditional Decoders in Diverse BCI Tasks
Are Global Dependencies Necessary? Scalable Time Series Forecasting via Local Cross-Variate Modeling
A Relative Error-Based Evaluation Framework of Heterogeneous Treatment Effect Estimators
Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory
A Representer Theorem for Hawkes Processes via Penalized Least Squares Minimization
Are Reasoning LLMs Robust to Interventions on their Chain-of-Thought?
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
A Resolution-Agnostic Geometric Transformer for Chromosome Modeling Using Inertial Frame
A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning
Are we measuring oversmoothing in graph neural networks correctly?
ARFlow: Auto-regressive Optical Flow Estimation for Arbitrary-Length Videos via Progressive Next-Frame Forecasting
Aria: an Agent for Retrieval and Iterative Auto-Formalization via Dependency Graph
A Rich Knowledge Space for Scalable Deepfake Detection
ARINBEV: Bird's-Eye View Layout Estimation with Conditional Autoregressive Model
ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting
ARTDECO: Toward High-Fidelity On-the-Fly Reconstruction with Hierarchical Gaussian Structure and Feed-Forward Guidance
Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement
ArtUV: Artist-style UV Unwrapping
ArtVIP: Articulated Digital Assets of Visual Realism, Modular Interaction, and Physical Fidelity for Robot Learning
A Scalable Constant-Factor Approximation Algorithm for $W_p$ Optimal Transport
A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration
A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction
A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
A Schrödinger Eigenfunction Method for Long-Horizon Stochastic Optimal Control
ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII Art
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
A Sharp KL Convergence Analysis for Diffusion Models under Minimal Assumptions

« prev Page 6/108 next »