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
BRIDGE: Triangular Fixed-Point Refinement for Long-Horizon Persona Consistency
Bridging Dynamics and Data: A Unified Diffusion Framework for Mechanistically-Informed Epidemic Forecasting
Bridging Functional and Representational Similarity via Usable Information
Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation
Bridging Local–Global Dissonance: Learning from Compressive Measurements for Hyperspectral Reconstruction
Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training
Bridging RGB and RAW: Single-step Deterministic Flow with Homogeneous Representation Alignment
Bridging Spherical Black-Box Optimizers
Bridging Structure and Semantics: Uncertainty-Modulated Dual-Path Diffusion for Robust Text-Attributed Graph Learning
Bridging the Gap Between Average and Discounted TD Learning
Bridging the Grounding Gap in VideoQA via Typed Memory for Language-based Belief-State Reasoning
Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions
Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA
Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models
Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting
Bridging Tokens and Geometry: Token-wise 3D Supervision for CAD Generation
Bridging Your Imagination with Audio-Video Generation via a Unified Director
Bring Future Vision: Dynamic Computation Allocation Guided by Lightweight Feature Forecaster
Bringing Code ALIVE: Optimizing Interactive Frontend Mini-Games via Automated Play and Reinforcement Learning at Scale
Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting
Broadening the Backdoor Basin: Understanding LLM Backdoors Collapse and Making Backdoors Persistent
BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs
BroRL: Scaling Reinforcement Learning via Broadened Exploration
B-Spar: Bayesian Sparse-Reward Modeling for RL-based Image Editing
BTSP-CAM: A Brain-Inspired Geometric Memory for Class-Incremental Learning
BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning
Budget-Constrained Step-Level Diffusion Caching
Budgeted Active Experimentation for Treatment Effect Estimation from Observational and Randomized Data
Budget-Efficient Attacks and Robustness Training for Cooperative MARL
Budget-Feasible Mechanisms for Submodular Welfare Maximization in Procurement Auctions
BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction
Building Reliable Long-Form Generation via Hallucination Rejection Sampling
Building Social World Models with Large Language Models
Building Social World Model with Large Language Models
Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination
Bullet Trains: Parallelizing Training of Temporally Precise Spiking Neural Networks
Butterworth as Attention: Anisotropic Spectral Gating for Pansharpening
BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
Byte Pair Encoding for Efficient Time Series Forecasting
C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
Cache Coherent Resampling for Efficient Test Time Scaling in LLM Reasoning via Adaptive Sequential Monte Carlo
CacheEdit: Efficient Multi-round Image Editing via Adaptive Token-wise Reuse.
CACR: Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning
CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
CAffNet: Hard Constraint-Affine Neural Networks
Calibrated Knowledge Aggregation in Bayesian Mixture-of-Experts for Continual VQA
Calibrated Multimodal Representation Learning with Missing Modalities
Calibrated Preference Learning: The Case of Label Ranking
Calibrated Test-Time Guidance for Bayesian Inference

« prev Page 16/130 next »