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
Pushing the Limits of Block Rotations in Post-Training Quantization
Push, Pop, Parallelize: Stack-Augmented Linear Attention via the Delta Rule
PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Fine-Grained Expert Merging and Bit-packed Inference
PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference
PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation
PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning
PyVision-RL: Forging Open Agentic Vision Models via RL
Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation
Q-Delta: Beyond Key–Value Associative State Evolution
Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
QEDBench: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs
Q-Flow: Stable and Expressive Reinforcement Learning with Flow-based Policy
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QiMeng-ChipV-RTL: Exploiting Information Locality for IP-level Verilog Generation
QiMeng-LibBench: Benchmarking LLM Agents for Library-Scale Cross-Architecture Migration
QiMeng-PerceptOS: Semantic-Aware Kernel Optimization for OS-Intensive Workloads via Hardware-Software Alignment
QPKO: Differentiable QP-Embedded Deep Koopman Framework for Modeling Nonlinear Systems
QPoint: End-to-End Lightweight Point Cloud Processing via Robust Quaternion Feature Learning
Q-SAM: Unlocking Sharpness-Aware Minimization for Generalization in Offline Reinforcement Learning
Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
Q-Tab: Quantized Tabular Data Generator
QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis
Quantifying and Optimizing Simplicity via Polynomial Representations
Quantifying Biases in LLM-as-a-Judge Evaluations
Quantifying Cross-Domain Knowledge Distillation in the Presence of Domain Shift
Quantifying Error Propagation and Model Collapse in Diffusion Models
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
Quantifying the Generalization Gap in Seizure Detection: A Large-Scale Empirical Benchmark via the SzCORE Challenge
Quantifying the noise sensitivity of the Wasserstein metric for images
Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles
Quantile-Free Uncertainty Quantification in Graph Neural Networks
Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning
Quantum Algorithms for Triangle Cut Sparsification
QuantumBoost: A lazy, yet fast, quantum algorithm for learning with weak hypotheses
Quantum latent distributions in deep generative models
Quantum Robust Inner Minimization for Reinforcement Learning with Quadratic Speed-Up in Query Complexity
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
QuantWear: Quantum-scale Wear Particle Detection for Jet Engine Diagnosis
QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
Quaternion Self-Attention with Shared Scores
QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
Query-Based Asymmetric Modeling with Decoupled Input–Output Rates for Speech Restoration
Query Circuits: Explaining How Language Models Answer User Prompts
Query-efficient model evaluation using cached responses
Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better

« prev Page 90/130 next »