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
Less Is More: Elevating RAG via Performance-Driven Context Compression
Less Is More: Fast and Accurate Reasoning with Cross-Head Unified Sparse Attention
Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure
Less Is More in Federated Continual Learning: RieSelect for Conflict-Aware Layer Selection in LLMs
Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization’s Impact on VLMs Beyond Accuracy
Less Token, More Signal: MoE Expert Pruning via Critical Token Selection
Let EEG Models Learn EEG
Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation
Let the Prototype Guide You: Robust Aggregation of Sparse Multi-Class Annotations via Annotator Prototype Learning
Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching
Leveraging Evidence Priors for Robust Prompt Learning under Noisy Supervision in Vision-Language Models
Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Systems
Leveraging Lineage Barcodes as Natural Augmentations for Contrastive Learning of Cell Fate in scRNA-seq Data
Leveraging Machine Unlearning for Cost-Efficient Preference Alignment
LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
Lie-Algebraic Acceleration of Neural Koopman Dynamics
LieStoNet: Learning Lie Symmetries from Spatiotemporal Data for Stochastic Dynamical Systems
LieWarper: Geometry-Aware Motion Transfer via Lie Algebra
LIF Recurrent Memory Enables Long-Horizon Spiking Computation
LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection
LightAVSeg: Lightweight Audio-Visual Segmentation
Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
LightningRL: Breaking the Accuracy–Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning
Light Up Your Face: A Physically Consistent Dataset and Diffusion Model for Face Fill-Light Enhancement
Lightweight and Interpretable Transformer via Mixed Graph Algorithm Unrolling for Traffic Forecast
Lightweight and Interpretable Transformer via Unrolling of Mixed Graph Algorithms for Traffic Forecast
Lightweight Federated Incremental Learning via Decoupled Replay
LightWM: Training-Free Hierarchical Working Memory for Small Language Model Agents
Likelihood Matching for Diffusion Models
Likelihood over Estimation: Robust Quadratic Discriminant Analysis for Heavy-Tailed Distributions with Theory and Evidence
LILO: Bayesian Optimization with Natural Language Feedback
LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models
LIMMT: Less Is More for Motion Tracking
LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations
LiMuon: Light and Fast Muon Optimizer for Large Models
LineageFlow: Flow Matching for High-Fidelity Family-Aware Protein Sequence Generation
Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport
Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement
Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
Linearizing Vision Transformer with Test-Time Training
Linear Regression with Unknown Truncation Beyond Gaussian Features
LINGUA: Bridging the Grounding Gap in VideoQA via Typed Memory and Belief-State Reasoning
Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG
Linguistic Properties and Model Scale in Brain Encoding: From Small to Compressed Language Models
Linguistic Relative Policy Optimization for Video Anomaly Reasoning
Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise

« prev Page 65/130 next »