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
LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation
Logarithmic Switching Regret for Online Convex Optimization
Logical Guidance for the Exact Composition of Diffusion Models
LogicSAGE: Neuro-Symbolic Reasoning with Socratic-Guided Enhancement
Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration
Logit Distance Bounds Representational Similarity
Log-Normal Multiplicative Dynamics for Stable Low-Precision Deep Learning
LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining
Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
Long-term Fairness with Selective Labels
Lookahead-GCG: Improving Universal Multi-Model Optimization-Based Jailbreaking Attacks via Stochastic Nesterov Optimization
Lookahead Path Likelihood Optimization for Diffusion LLMs
Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models
Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
Lookahead Unmasking Elicits Reliable Decoding in Diffusion Language Models
Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation
Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning
LoPhyDA: Low-Rank Tensor and Physics Gradient Guided Diffusion for Atmospheric Data Assimilation
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
LORD-GoF: A Robust Online Detection Approach for LLM Watermarks in Sparse and Mixed Streams
LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
LoRe: Adaptive Interaction-Evaluation Routing with Per-step Interaction Budgets for Iterative Graph Solvers
LoSA: Locality Aware Sparse Attention in Diffusion Language Models
Loss-Aware Distributionally Robust Optimization via Trainable Optimal Transport Ambiguity Sets
Lost in Context: Addressing Context Anxiety in Large Language Models
Lost in Context: Adressing Context Anxiety in Large Language Models
LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry
Lottery Prior: Randomized Neural Compression for Zero-Shot Inverse Problems
LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation
Low-Compute Watermark Removal via Dual-Domain Natural Projection
Low-cost Full Fine-tuning: Learning What to Update for LLMs
Low-dimensional topology of deep neural networks
Lower Bounds for Frank-Wolfe on Strongly Convex Sets
Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles
Low Kruskal-Rank Adaptation
Low-Rank and Sparsity Are All You Need: Exploring Robust Hierarchical Latent Subspaces for Transferable Adversarial Attack
LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents
LS$^{2}$MC-GDA: A Smoothed Algorithm for Federated Stochastic Multi-Level Compositional Minimax Optimization
LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution
L-SR1: Learned Symmetric-Rank-One Preconditioning
LUCID: Attention with Preconditioned Representations
LUGS: Latent-aware Guidance for Efficient Unmasking in Diffusion Large Language Models
LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
LVCG: Learning ECG Representations in the Latent Vectorcardiogram Space
MA$^3$S: Model-Agnostic Active Annotation Strategy for Crowdsourcing

« prev Page 67/130 next »