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
Does “Do Differentiable Simulators Give Better Policy Gradients?” Give Better Policy Gradients?
Does FLUX Already Know How to Perform Physically Plausible Image Composition?
Does Higher Interpretability Imply Better Utility? A Pairwise Analysis on Sparse Autoencoders
Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level Tasks
Does Weak-to-strong Generalization Happen under Spurious Correlations?
DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series
Do Large Language Models Know What They Are Capable Of?
Do LLM Agents Know How to Ground, Recover, and Assess? Evaluating Epistemic Competence in Information-Seeking Agents
Do LLMs Forget What They Should? Evaluating In-Context Forgetting in Large Language Models
Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation
Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
Don't Just Fine-tune the Agent, Tune the Environment
Don’t Pass@k: A Bayesian Framework for Large Language Model Evaluation
Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models
Don't Shift the Trigger: Robust Gradient Ascent for Backdoor Unlearning
Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search
Don't Throw Away Your Pretrained Model
DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs
Doubly-Regressing Approach for Subgroup Fairness
Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas
DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?
Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion Models
Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
DPad: Efficient Diffusion Language Models with Suffix Dropout
dParallel: Learnable Parallel Decoding for dLLMs
DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
DPQuant: Efficient and Private Model Training via Dynamic Quantization Scheduling
Draft-based Approximate Inference for LLMs
DragFlow: Unleashing DiT Priors with Region-Based Supervision for Drag Editing
Dragging with Geometry: From Pixels to Geometry-Guided Image Editing
DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
DRBench: A Realistic Benchmark for Enterprise Deep Research
DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision
DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents
DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing
D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping
DR-GGAD: Dual Residual Centering for Mitigating Anomaly Non‑Discriminativity in Generalist Graph Anomaly Detection
DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems
DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense
DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning
DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models
DRIFT-Net: A Spectral-Coupled Neural Operator for PDEs Learning
DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking
DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving

« prev Page 26/108 next »