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
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models
FOVI: A biologically-inspired foveated interface for deep vision models
Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
FPTQuant: Function-Preserving Transforms for LLM Quantization
FRACTAL: State Space Model with Fractional Recurrent Architecture for Computational Temporal Analysis of Long Sequences
Fractional is Better: Learnable Derivative Orders in Neural Operator Learning
FrameOracle: Learning What to See and How Much to See in Videos
FreeRet: MLLMs as Training-Free Retrievers
FreeText: Training-Free Text Rendering via Attention Localization and Spectral Glyph Injection
Frequency-Aware Perceptual Optimization for Low-Complexity Implicit Image Compression
Frequency Matching in Spiking Neural Networks for mmWave Sensing
Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference
Frictional Q-Learning
FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time
FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision–Language Models
From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning
From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
From Basis to Basis: Gaussian Particle Representation for Interpretable PDE Operators
From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
From Coarse to Fine: Deep Prototype Refinement Network for Few-Shot Point Cloud Semantic Segmentation
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations
From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models
From Denoising to De-Channeling: Integrating Physical Channel Priors into Diffusion Models for Radio Signal Understanding
From Diagrams to Code: Multilingual Programming with Visual Design
From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
From Distribution to Geometry: Stable Graph Generalization via Invariant Barycenters
From Drift to Coherence: Stabilizing Beliefs in LLMs
From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide ML Interatomic Potential Architectures
From Extraction to Deduction: Resolving Functional Misalignment in RAG via a Collaborative Critic-Reasoner Framework
From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data
From Feasible to Practical: Pareto-Optimal Synthesis Planning
From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity
From Generalist to Specialist Representation
From Generative to Episodic: Sample-Efficient Replicable Reinforcement Learning
From geometry to dynamics: Learning overdamped Langevin dynamics from sparse observations with geometric constraints
From Growing to Looping: A Unified View of Iterative Computation in LLMs
From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion
From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
From Holo Pockets to Electron Density: GPT-style Drug Design with Density
From Human Labels to Literature: Semi-Supervised Learning of NMR Chemical Shifts at Scale
From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation
From Individual Calibration to Reliable Classifiers: ALD Parameterization with mPAIC Guarantees
From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping
From Interactions to Principles: Experience-Driven Self-Distillation for Evolving LLM Agents
From Interaction Trajectories to Prompt Rules: Credit Assignment for Multi-Agent Prompt Optimization

« prev Page 45/130 next »