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
FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference
Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation
FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning
Fast Proteome-Scale Protein Interaction Retrieval via Residue-Level Factorization
Fast training of accurate physics-informed neural networks without gradient descent
FastVGGT: Fast Visual Geometry Transformer
FastVMT: Eliminating Redundancy in Video Motion Transfer
FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty Levels
Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs
FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
Feature compression is the root cause of adversarial fragility in neural networks
Feature segregation by signed weights in artificial vision systems and biological models
Features Emerge as Discrete States: The First Application of SAEs to 3D Representations
FeDaL: Federated Dataset Learning for General Time Series Foundation Models
FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments
Fed-Duet: Dual Expert-Orchestrated Framework for Continual Federated Vision-Language Learning
Federated ADMM from Bayesian Duality
Federated Graph-Level Clustering Network with Dual Knowledge Separation
Federated Learning of Quantile Inference under Local Differential Privacy
Federated Learning with Profile Mapping under Distribution Shifts and Drifts
FedMC: Federated Manifold Calibration
FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
FedOpenMatch: Towards Semi-Supervised Federated Learning in Open-Set Environments
Feedback-driven recurrent quantum neural network universality
FERD: Fairness-Enhanced Data-Free Adversarial Robustness Distillation
FETAL-GAUGE: A BENCHMARK FOR ASSESSING VISION-LANGUAGE MODELS IN FETAL ULTRASOUND
Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM Evaluation
Fewer Weights, More Problems: A Practical Attack on LLM Pruning
FHE-Coder: Benchmarking Secure Agentic Code Generation for Fully Homomorphic Encryption
FictionalQA: A Dataset for Studying Memorization and Knowledge Acquisition
FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring
FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
Figma2Code: Automating Multimodal Design to Code in the Wild
FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
Fine-Grained Activation Steering: Steering Less, Achieving More
Fine-Grained Class-Conditional Distribution Balancing for Debiased Learning
Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems by Exploiting Knowledge Asymmetry
Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
Fine-tuning Behavioral Cloning Policies with Preference‑Based Reinforcement Learning
Fine-Tuning Diffusion Models via Intermediate Distribution Shaping
Fine-tuning Done Right in Model Editing
Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach
FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents
Finite-Time Analysis of Actor-Critic Methods with Deep Neural Network Approximation
Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants
FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

« prev Page 34/108 next »