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
AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design
AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical Functions
AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
AutoRAS: Learning Robust Agentic Systems with Primitive Representations
Autoregression with Self-Token Prediction
Autoregressive Boltzmann Generators
Autoregressive Direct Preference Optimization
Autoregressive Image Generation with Masked Bit Modeling
Auto-regressive In-context Demonstration Selection
Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction
Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions
AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agents
AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic
AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines
AvAtar: Learning to Align via Active Optimal Transport
A Very Big Video Reasoning Suite
AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
Avoid What You Know: Divergent Trajectory Balance for GFlowNets
AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes
Awakening Visual Reasoning: Mitigating Post-Training Failure in Vision-Text Compression
Axiomatic Atlas: A Prescriptive Framework for Neural Architecture Design
BabyVision: Visual Reasoning Beyond Language
Backjump-on-Graph: Empowering Large Language Models with Reinforced Retrospective Exploration for Agentic Knowledge Graph Reasoning
Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?
Backward SDE–Based Diffusion for Physics-Constrained Generation
Backward SDEs-based Diffusion for Physics-Constrained Generation
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
Baguan-TS: A Sequence-Native In-Context Learning Model for Time Series Forecasting with Covariates
Baguan-TS: dual in-context learning model for time series forecasting with covariates
Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective
Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
Balancing Plasticity and Stability with Fast and Slow Successor Features
Balancing Understanding and Generation in Discrete Diffusion Models
BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields
Bandit Social Leaning Dynamics with Exploration Episodes
Bandit Social Learning with Exploration Episodes
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate
Barriers to Counterfactual Credit Attribution for Autoregressive Models
BAS: Bridging Adam and SignSGD for Memory-Efficient LLM Training
Base Models Know How to Reason, Thinking Models Learn When
BASIL: Scalable Bayesian Semi-supervised Clustering with Feature Selection and Adaptive Constraint Weighting
BAT: Better Audio Transformer Guided by Convex Gated Probing
Batched Contextual Reinforcement
Batched First-Order Methods for Parallel LP Solving in MIP
Batch Normalization for Neural Networks on Complex Domains

« prev Page 11/130 next »