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
Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
Efficient Offline Reinforcement Learning via Peer-Influenced Constraint
Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation
Efficient Prediction of Large Protein Complexes via Subunit-Guided Hierarchical Refinement
Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees
Efficient Reasoning with Balanced Thinking
Efficient Regression-based Training of Normalizing Flows for Boltzmann Generators
Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
Efficient Resource-Constrained Training of Transformers via Subspace Optimization
Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
Efficient Sliced Wasserstein Distance Computation via Adaptive Bayesian Optimization
Efficient Submodular Maximization for Sums of Concave over Modular Functions
Efficient Testing for Correlation Clustering: Improved Algorithms and Optimal Bounds
Efficient Test-Time Scaling for Small Vision-Language Models
Efficient Turing Machine Simulation with Transformers
Efficient Zero-shot Inpainting with Decoupled Diffusion Guidance
EffiVMT: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning
Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking
EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph
EgoBrain: Synergizing Minds and Eyes For Human Action Understanding
EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning
EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
EgoTwin: Dreaming Body and View in First Person
EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations
Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG
EigenBench: A Comparative Behavioral Measure of Value Alignment
EigenScore: OOD Detection using Posterior Covariance in Diffusion Models
Einstein Fields: A Neural Perspective To Computational General Relativity
EIP: Weighted Ranking of LLMs by Quantifying Question Difficulty
Elastic Optimal Transport: Theory, Application, and Empirical Evaluation
ELEPHANT: Measuring and understanding social sycophancy in LLMs
Eliciting Harmful Capabilities by Fine-Tuning on Safeguarded Outputs
Eliciting Numerical Predictive Distributions of LLMs Without Auto-Regression
Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
Eliminating VAE for Fast and High-Resolution Generative Detail Restoration
ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems
ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
Embedding-Based Context-Aware Reranker
Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
Embodied Navigation Foundation Model
Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning
EMBridge: Enhancing Gesture Generalization from EMG Signals Through Cross-modal Representation Learning
Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator
Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought
Emergent Coordination in Multi-Agent Language Models
Emergent Dexterity Via Diverse Resets and Large-Scale Reinforcement Learning

« prev Page 29/108 next »