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
Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
Dynamic Weight Grafting: Localizing Finetuned Factual Knowledge in Transformers
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive Sharing
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
EA3D: Event-Augmented 3D Diffusion for Generalizable Novel View Synthesis
EAMET: ROBUST MASSIVE MODEL EDITING VIA EMBEDDING ALIGNMENT OPTIMIZATION
Early Signs of Steganographic Capabilities in Frontier LLMs
Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents
EarthSE: A Benchmark Evaluating Earth Scientific Exploration Capability for Large Language Models
Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
EAST: Early Action Prediction Sampling Strategy with Token Masking
EasyCreator: Empowering 4D Creation through Video Inpainting
EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning
EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model
EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models
EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer
ECHO: Toward Contextual Seq2Seq Paradigms in Large EEG Models
Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
EdgeCape: Edge Weight Prediction For Category-Agnostic Pose Estimation
EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements
Edit-Based Flow Matching for Temporal Point Processes
EditBench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits
EditLens: Quantifying the Extent of AI Editing in Text
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling
EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing
EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget
Efficient Adversarial Attacks on High-dimensional Offline Bandits
Efficient Agent Training for Computer Use
Efficient algorithms for Incremental Metric Bipartite Matching
Efficient and Sharp Off-Policy Learning under Unobserved Confounding
Efficient Approximate Posterior Sampling with Annealed Langevin Monte Carlo
Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention
Efficient Autoregressive Inference for Transformer Probabilistic Models
Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
Efficient Credal Prediction through Decalibration
Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
Efficient Differentiable Contact Model with Long-range Influence
Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
Efficient Ensemble Conditional Independence Test Framework for Causal Discovery
Efficient Estimation of Kernel Surrogate Models for Task Attribution
Efficient Learning on Large Graphs using a Densifying Regularity Lemma
Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
Efficient Message-Passing Transformer for Error Correcting Codes
Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimization
Efficient Multimodal Spatial Reasoning via Dynamic and Asymmetric Routing

« prev Page 28/108 next »