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
Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products
ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Extending Fourier Neural Operators for Modeling Parameterized and Coupled PDEs
Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction
Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding
Extreme Weather Nowcasting via Local Precipitation Pattern Prediction
FACET: A Fragment-Aware Conformer Ensemble Transformer
FACM: Flow-Anchored Consistency Models
FACT: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
FACT: Fine-grained Across-variable Convolution for Multivariate Time Series Forecasting
Factuality Matters: When Image Generation and Editing Meet Structured Visuals
Fair Classification by Direct Intervention on Operating Characteristics
Fair Conformal Classification via Learning Representation-Based Groups
Fair Decision Utility in Human-AI Collaboration: Interpretable Confidence Adjustment for Humans with Cognitive Disparities
Fair Graph Machine Learning under Adversarial Missingness Processes
Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs
Fairness-Aware Multi-view Evidential Learning with Adaptive Prior
Fairness via Independence: A General Regularization Framework for Machine Learning
Fair Reinforcement Learning for Just AI
FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning
Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
Faithfulness Under the Distribution: A New Look at Attribution Evaluation
FakeXplain: AI-Generated Image Detection via Human-Aligned Grounded Reasoning
Falcon: Fast Proximal Linearization of Normalized Cuts for Unsupervised Image Segmentation
FALCON: Few-step Accurate Likelihoods for Continuous Flows
FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
FAME: Formal Abstract Minimal Explanation for Neural Networks
Fantastic Pretraining Optimizers and Where to Find Them
Fantastic Tractor-Dogs and How Not to Find Them With Open-Vocabulary Detectors
FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
FARI: Robust One-Step Inversion for Watermarking in Diffusion Models
FARTrack: Fast Autoregressive Visual Tracking with High Performance
FASA: FREQUENCY-AWARE SPARSE ATTENTION
FaSTA*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
Fast and Interpretable Protein Substructure Alignment via Optimal Transport
Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry
FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers
Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws
Fast Convergence of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
Fast Data Mixture Optimization via Gradient Descent
FAST‑DIPS: Adjoint‑Free Analytic Steps and Hard‑Constrained Likelihood Correction for Diffusion‑Prior Inverse Problems
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Fast-dLLM v2: Efficient Block-Diffusion LLM
Faster Gradient Methods for Highly-smooth Stochastic Bilevel Optimization
FASTer: Toward Powerful and Efficient Autoregressive Vision–Language–Action Models with Learnable Action Tokenizer and Block-wise Decoding
Faster Vision Transformers with Adaptive Patches
Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances

« prev Page 33/108 next »