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
Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences
DispViT: Direct Stereo Disparity Regression with a Single-Stream Vision Transformer
DiSRouter: Distributed Self-Routing for LLM Selections
Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models
Dissecting Representation Misalignment in Contrastive Learning via Influence Function
DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
DistDF: Time-series Forecasting Needs Joint-distribution Wasserstein Alignment
Distillation of Large Language Models via Concrete Score Matching
Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling
Distilling and Adapting: A Topology-Aware Framework for Zero-Shot Interaction Prediction in Multiplex Biological Networks
Distilling Causal Signals for One-Shot Directed Evolution of Antibodies
Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Reasoning Large Language Models
Distilling to Hybrid Attention Models via KL-Guided Layer Selection
DistillKac: Few-Step Image Generation via Damped Wave Equations
DistMLIP: A Distributed Inference Platform for Machine Learning Interatomic Potentials
Distractor-free Generalizable 3D Gaussian Splatting
Distributed Algorithms for Euclidean Clustering
Distributional Consistency Loss: Beyond Pointwise Data Terms in Inverse Problems
Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and Learning
Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation
Distributionally Robust Cooperative Multi-agent Reinforcement Learning with Value Factorization
Distributionally Robust Linear Regression with Block Lewis Weights
Distributionally Robust Optimization via Generative Ambiguity Modeling
Distributional Machine Unlearning via Selective Data Removal
Distributional value gradients for stochastic environments
Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
Distribution-Aware Multi-Granularity Phase Coding: Towards Lower Conversion Error for Spike-Driven Large Language Models
Distribution-informed Online Conformal Prediction
Distributions as Actions: A Unified Framework for Diverse Action Spaces
DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage
DiVE-k: DIFFERENTIAL VISUAL REASONING FOR FINE-GRAINED IMAGE RECOGNITION
DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
Divergence-Free Neural Networks with Application to Image Denoising
Diverse and Sparse Mixture-of-Experts for Causal Subgraph–Based Out-of-Distribution Graph Learning
Diverse Dictionary Learning
DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration
Diverse Text Decoding via Iterative Reweighting
Diverse Text-to-Image Generation via Contrastive Noise Optimization
Diversified Multinomial Logit Contextual Bandits
Diversity-Enhanced Reasoning for Subjective Questions
Diversity-Incentivized Exploration for Versatile Reasoning
Divid: Disentangled Spatial-Temporal Modeling within LLMs for Temporally Grounded Video Understanding
Divide and Abstract: Autoformalization via Decomposition and Abstraction Learning
Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models
DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction
DMAP: A Distribution Map for Text
DND: Boosting Large Language Models with Dynamic Nested Depth
DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD
Do 3D Large Language Models Really Understand 3D Spatial Relationships?
Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning

« prev Page 25/108 next »