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
Deep Global-sense Hard-negative Discriminative Generation Hashing for Cross-modal Retrieval
Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models
Deep-ICE: The first globally optimal algorithm for empirical risk minimization of two-layer maxout and ReLU networks
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios
Deep Learning for Subspace Regression
Deep Learning with Learnable Product-Structured Activations
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
DeepPrim: a Physics-Driven 3D Short-term Weather Forecaster via Primitive Equation Learning
DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
DeepSADR: Deep Transfer Learning with Subsequence Interaction and Adaptive Readout for Cancer Drug Response Prediction
DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Tree-based Search
Deep SPI: Safe Policy Improvement via World Models
Deep Think with Confidence
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights
Defending against Backdoor Attacks via Module Switching
DefensiveKV: Taming the Fragility of KV Cache Eviction in LLM Inference
Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-Experts
Delay Flow Matching
DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models
DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining
Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring
Delving into Spectral Clustering with Vision-Language Representations
DeMo: Decoupled Momentum Optimization
DemoGrasp: Universal Dexterous Grasping from a Single Demonstration
Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
Demystifying Deep Search: A Holistic Evaluation with Hint-free Multi-Hop Questions and Factorised Metrics
Demystifying Robot Diffusion Policies: Action Memorization and a Simple Lookup Table Alternative
Demystifying Supervision Data Generalization in Multimodal LMs
Demystifying The Mechanisms Behind Emergent Exploration in Goal-Conditioned RL
Denoising Neural Reranker for Recommender Systems
DeNOTS: Stable Deep Neural ODEs for Time Series
Dens3R: A Foundation Model for 3D Geometry Prediction
DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment
Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks
Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
Depth Anything 3: Recovering the Visual Space from Any Views
Depth Anything with Any Prior
DepthLM: Metric Depth from Vision Language Models
DeRaDiff: Denoising Time Realignment of Diffusion Models
Derandomized Online-to-Non-convex Conversion for Stochastic Weakly Convex Optimization
DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning
Designing Affine-Invariant Neural Networks for Photometric Corruption Robustness and Generalization
Designing Rules to Pick a Rule: Aggregation by Consistency
Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning
DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models

« prev Page 22/108 next »