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
AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration
AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
Alternating Diffusion for Proximal Sampling with Zeroth Order Queries
Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering
AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
A Memory-Efficient Hierarchical Algorithm for Large-scale Optimal Transport Problems
AMiD: Knowledge Distillation for LLMs with $\alpha$-mixture Assistant Distribution
A Minimum Variance Path Principle for Accurate and Stable Score-Based Density Ratio Estimation
AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation
Amortising Inference and Meta-Learning Priors in Neural Networks
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
Analysis of approximate linear programming solution to Markov decision problem with log barrier function
Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis
Analyzing and Evaluating Unbiased Language Model Watermark
Analyzing the Training Dynamics of Image Restoration Transformers: A Revisit to Layer Normalization
Anatomy-aware Representation Learning for Medical Ultrasound
Anchored Supervised Fine-Tuning
Anchor Frame Bridging for Coherent First-Last Frame Video Generation
A Near-Optimal Best-of-Both-Worlds Algorithm for Federated Bandits
An efficient, provably optimal algorithm for the 0-1 loss linear classification problem
An Efficient SE(p)-Invariant Transport Metric Driven by Polar Transport Discrepancy-based Representation
An Ensemble Framework for Unbiased Language Model Watermarking
AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMs
An evolutionary perspective on modes of learning in Transformers
A New Approach to Controlling Linear Dynamical Systems
A New Initialization to Control Gradients in Sinusoidal Neural Networks
A New Paradigm for Genome-wide DNA Methylation Prediction Without Methylation Input
Angle K-Means
Animal behavioral analysis and neural encoding with transformer-based self-supervised pretraining
Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models
Anime-Ready: Controllable 3D Anime Character Generation with Body-Aligned Component-Wise Garment Modeling
An Improved Model-free Decision-estimation Coefficient with Applications in Adversarial MDPs
An Information-Theoretic Framework For Optimizing Experimental Design To Distinguish Probabilistic Neural Codes
An Information-Theoretic Parameter-Free Bayesian Framework for Probing Labeled Dependency Trees from Attention Score
An Information Theoretic Perspective on Agentic System Design
Annotation-Efficient Honesty Alignment via Confidence Elicitation and Calibration
A Noise is Worth Diffusion Guidance
An Open-Ended Benchmark and Formal Framework for Adjuvant Research with MLLM
An Optimal Diffusion Approach to Quadratic Rate-Distortion Problems: New Solution and Approximation Methods
An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes
Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
AntigenLM: Structure-Aware DNA Language Modeling for Influenza
Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
Antithetic Noise in Diffusion Models
AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
Any-Order Flexible Length Masked Diffusion
Any-step Generation via N-th Order Recursive Consistent Velocity Field Estimation
Any-Subgroup Equivariant Networks via Symmetry Breaking

« prev Page 5/108 next »