ICML 2026

6,487 papers

Top Research Directions

Research directions most represented by ICML 2026 papers.

Scaling Language Model Reasoning Beyond Verifiable Rewards 79
Group Relative Policy Optimization for Large Reasoning Models 63
General Purpose Reasoning from Specialized Reinforcement Learning 62
Overcoming the Iterative Inference Latency of Diffusion Models 50
Shifting from Static Benchmarks to Dynamic Evaluation 47
Controlling Language Models Through Latent Space Interventions 45
Resolving Superposition with Sparse Autoencoders 42
Autonomous Code Refinement via Execution Feedback Loops 41
The Performance Cliff in Ultra Low Bit Quantization 41
Activation Steering for Inference Time Model Control 39
Mitigating Expert Collapse in Sparse Mixture of Experts 37
Proxy Objective Exploitation in Language Model Alignment 37
The Decoupling of Visual Perception and Logical Reasoning 36
Mitigating Computational Overthinking in Large Reasoning Models 35
Input Adaptive Compute Allocation for Language Models 33

Top Authors

AuthorPapers
Junchi Yan19
Min Zhang19
Tat-Seng Chua15
Haoxuan Li14
Philip Torr14
Yong Li14
Kun Zhang13
Li Shen13
Tianlong Chen13
Xiang Wang13
Xin Geng13
Yejin Choi13
Bo An12
Mihaela van der Schaar12
Xunliang Cai12
Bo Han11
Ge Zhang11
Han Liu11
Jiang Bian11
LEI BAI11

Impactful Papers

Papers from ICML 2026 that shaped research clusters.

Foundational

Papers

Title
World-Shaper: A Unified Framework for 360° Panoramic Editing
WorldTravel: A Realistic Multimodal Travel-Planning Benchmark with Tightly Coupled Constraints
WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition
X-EviProbe: Post-hoc Parameter-Free Evidential Uncertainty Quantification for Frozen Graph Neural Networks
xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
X-MoGe: A Cross-Modal Adaptation Framework with Mixture-of-Experts and Geometry Guidance for Heterogeneous Collaborative Perception
XPERT: Expert Knowledge Transfer for Effective Training of Language Models
XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations
XRPO: Pushing the Limits of GRPO with Targeted Exploration and Exploitation
XSkill: Continual Learning from Experience and Skills in Multimodal Agents
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge
XYZFlow: Scaling Multidimensional Shortcut Flows for Efficient Generative Modeling
You Can Learn Tokenization End-to-End with Reinforcement Learning
You Don’t Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
You Don't Protect if You Don't Expect: Breaking the Key Assumption behind CLIP's Test-Time Defenses
You Need Better Attention Priors
Z-Erase: Enabling Concept Erasure in Single Stream Diffusion Transformers
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
ZeroDiff: Zero-Shot Time Series Reconstruction via Informed-Prior Diffusion
Zero-Flow Encoders
Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation
Zero-shot Active Mapping via Fused 360-BEV Representations and Vision–Language Models
Zero-Shot Off-Policy Learning
Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language
Zero-Shot Text-to-Motion Evaluation using Video Language Models
Zero-source LLM Hallucination Detection with Human-like Criteria Probing
Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression
Zeroth-Order Forward-Only SNN Training Inspiring Neuromorphic On-Chip Learning
Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problems
Zeroth-Order Optimization at the Edge of Stability
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

« prev Page 130/130