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
Beyond Softmax: A Natural Parameterization for Categorical Random Variables
Beyond Static Allocation: Dynamic Sensitivity-Aware Fine-Tuning for Vision Transformers
Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL
Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability
Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts
Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?
Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting
Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving
Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
Beyond Tokens: Enhancing RTL Quality Estimation via Structural Graph Learning
Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
Beyond Unidirectional Bias: Reciprocal Perspective Calibration in Scene Graph Generation
Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
BFCL Audio: An Audio Function Calling Evaluation for Large Language Models
BFS-Prover-V2: Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
BFTS: Thompson Sampling with Bayesian Additive Regression Trees
Bi-Anchor Interpolation Solver for Accelerating Generative Modeling
Biased Generalization in Diffusion Models
Biases in the Blind Spot: Detecting What LLMs Fail to Mention
Bias in Zeroth-Order Normal Estimation for Decision-Based Attacks
Bias-Spectrum Neural Processes for Parametric PDEs: Architecture Priors Meet PDE Constraints
BiCrossNet with Decoupled Dual Generators: A Parameter‑Efficient and Generalizable Few‑Shot Custom Gesture Recognition Framework
Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
Bilinear Bandits with Partially Observable Features
Bimodal masked language modeling for bulk RNA-seq and DNA methylation representation learning
Bioacoustic Geolocation: Species Sounds as Geographic Signals
BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics
BIOARC: Discovering Optimal Neural Architectures for Biological Foundation Models
BioDynaSpec: Harmonic-Guided Spatio-Spectral Autoregressive Diffusion for Protein Dynamics Generation
BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data
Biologically plausible heavy-tailed connectivity enhances generalizations on cognitive tasks in recurrent neural networks
BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science
BioToken and BioFM – Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation Models
Bio-Vision-Inspired Spiking Neural Networks for Object Detection with Event Cameras
Bipartite Graph Attention-based Clustering for Large-scale scRNA-seq Data
BiRQA: Bidirectional Robust Quality Assessment for Images
BIT-LLM: Brain Instruction Tuned LLM with persistent Cross-Attention for fMRI-to-Text Decoding
BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
Bits That Count: Quantifying and Predicting Capabilities of Language Models
BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation
Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning
Black-Box Detection of LLM-Generated Text Using Generalized Jensen Shannon Divergence

« prev Page 14/130 next »