Training Data

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

13 new papers

A weekly snapshot of new work published in Training Data.

Inside this field

Focused directions

Focused topic

Training Data

Within Training Data

130 papersExplore

Focused topic

Trainability

Within Training Data

106 papersExplore

Focused topic

Model Training

Within Training Data

79 papersExplore

312 papers

Latest in Training Data

Browse all topics →

DMuon: Efficient Distributed Muon Training with Near-Adam Overhead
Jun 25, 2026Vincent Chen, Starrick Liu, Regis Cheng +8Muon Optimizer Muon
RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning
Jun 25, 2026Rongjian Chen, Jianmin Hu, Kejiang Ye +1Long Rollouts Rollout
Dataset Usage Inference without Shadow Models or Held-out Data
Jun 24, 2026Wojciech Łapacz, Stanisław Pawlak, Jan Dubiński +2Training Data Private Data
FUTO Swipe: Layout-Agnostic Neural Swipe Decoding
Jun 24, 2026David Lee Miller, Aleksandras KostarevasPublic Neuroqwerty Large Language Model Decoder
GCT-MARL: Graph-Based Contrastive Transfer for Sample-Efficient Cooperative Multi-Agent Reinforcement Learning
Jun 23, 2026Animesh Animesh, Satheesh K Perepu, Kaushik DeyMulti-Agent Reinforcement Learning Iterative Co-Training
Less is More: Quality-Aware Training Data Selection for Scientific Summarization
Jun 23, 2026Maria Nefeli Paraskevopoulou, Tatiana Passali, Grigorios TsoumakasSummarization Biomedical Text
BluTrain: A C++/CUDA Framework for AI Systems
Jun 23, 2026Adhitya Charan, Adwaid Suresh, Anuj Kumar +19Cuda Trainability
Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients
Jun 23, 2026Zhihao Zhu, Hongyi Tang, Yi Yang +1Vision-Language Training Data
Training Dynamics of Neural Software Defect Predictors under Coupled Data-Quality Issues
Jun 23, 2026Emmanuel Charleson Dapaah, Philip Makedonski, Jens GrabowskiClass Imbalance Training Data
Breaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech Extraction via Two-Stage Training
Jun 23, 2026Wonchul Shin, Inyong Choi, Kyogu LeeElectroencephalography Spatial Super-Resolution Model Training
MGI: Member vs Generated Inference
Jun 22, 2026Bihe Zhao, Michel Meintz, Juangui Xu +2Membership Inference Generative Models
ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation
Jun 22, 2026Chen Lin, Kedi Chen, Wei ZhangOn-Policy Distillation Trainability
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
Jun 22, 2026Zhanbo Hua, Yifan Yao, Weihao Xie +14Task Synthesis Workflow Generation
Training-free Task Classification for Multi-Task Model Merging
Jun 21, 2026Jungyong Son, Jinwook Jung, Sungyong BaikContinual Model Merging Multi--Task Learning
OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals
Jun 19, 2026Hongxu Su, Jianzhu Yao, Huan Zhang +2Trustworthy Artificial Intelligence Trainability
Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study
Jun 18, 2026Anton Abramochkin, Radu Timofte, Dmitry IgnatovNeural Architecture Search Adam
Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications
Jun 18, 2026Paul Koch, Vivek Chavan, André Sers +4Synthetic-To-Real Domain Gap Indoor Scene Generation
LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents
Jun 16, 2026Haoyang Fang, Wei Zhu, Boran Han +11Reinforcement Learning Post-Training Exploration-Exploitation Dilemma
TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins
Jun 16, 2026Yuxiang Luo, Haonan Long, Chen Wang +6Finetuning Tuning
Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics
Jun 16, 2026Xiyu Zhai, Xinyi Chen, Yiping Wang +3Theorem Mathematics
Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces
Jun 16, 2026Yahong Yang, Zecheng Zhang, Wei Zhu +2Logarithmic Sobolev Inequalities Probabilistic Operator Learning
ProCUA-SFT Technical Report
Jun 15, 2026Jaehun Jung, Ximing Lu, Brandon Cui +11Computer-Use Agents Agent Framework
On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies
Jun 15, 2026Sunwoo Kim, Sunkyung Lee, Clark Mingxuan Ju +5Large-Scale Recommendation Systems Recommendation
TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation
Jun 15, 2026Jielin Wu, Shenzhe Yao, Guanqi He +6Motion Retargeting Robotic Manipulation Policies
Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling
Jun 14, 2026Zhimin Li, Harshitha Menon, Charles Jekel +2Context Compression Training Data
AdaMame: A Training Recipe for Adaptive Multilingual Reasoning
Jun 13, 2026Dayeon Ki, Kevin Duh, Marine CarpuatMultilingual Reasoning Large Language Model Reasoning
SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents
Jun 11, 2026Ziyi Wang, Yuxuan Lu, Yimeng Zhang +8Personalized Large Language Model Agents Deep Reinforcement Learning
Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
Jun 10, 2026Romana Qureshi, Hafida Benhidour, Said Kerrache +1Heterogeneous Pruning Scores Sparse Deep Neural Network Accelerators
World Model Self-Distillation: Training World Models to Solve General Tasks
Jun 10, 2026Sebastian Stapf, Pablo Acuaviva Huertos, Aram Davtyan +1Large-Scale Video Generation Models Model Training
Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization
Jun 10, 2026Frank Xiao, Mary PhuongReinforcement Learning Post-Training Hacking
Fast Speech Foundation Model Distillation Using Interleaved Stacking
Jun 10, 2026Eungbeom Kim, Kyogu LeeSpeech Large Language Models Inference Latency
DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectors
Jun 10, 2026Jiale Deng, Yanyan Shen, Xiaogang Shi +1Training Data Training Data Attribution
i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
Jun 9, 2026Boya Zeng, Tianze Luo, Shu Pu +4Text-To-Image Diffusion Models Training Data
Piper: A Programmable Distributed Training System
Jun 9, 2026Megan Frisella, Shubham Tiwari, Andy Ruan +5Parallel Model Training
Massive Open-Vocabulary Keyword Spotting
Jun 9, 2026Leonor Barreiros, Raul Monteiro, Afonso Mendes +1Open-Vocabulary Training Data
Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs
Jun 9, 2026Ruixuan Huang, Jinyuan Shi, Hantao Huang +5Trainability Continual Learning Methods
Integral Field Unit Spectroscopy with One Fiber
Jun 8, 2026Zehao Peng, Biprateep Dey, Chris J. Maddison +1Spectra Cosmology
Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization
Jun 8, 2026Gennaro De LucaQuantum Machine Learning Quantum Circuit Simulation
A Theoretical Analysis of Memory and Overfitting Phenomena in Stochastic Interpolation Models
Jun 7, 2026Yunchen Li, Shaohui Lin, Zhou YuOverfitting Interpolation
Auditing Training Data in Domain-adapted LLMs: LoRA-MINT
Jun 5, 2026Gonzalo Mancera, Daniel DeAlcala, Aythami Morales +3Large Language Model Adaptation Membership Inference
Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2
Jun 5, 2026Daniel DeAlcala, Gonzalo Mancera, Julian Fierrez +3Membership Inference Algorithm Auditing
Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
Jun 5, 2026Yuan Zeng, Yujia Shi, Yuhao Yang +4Driving Co-Director
Adaptive Band Selection for Hyperspectral Classification with Spatially Disjoint Evaluation
Jun 4, 2026Ikram El-Hajri, Ouassim Karrakchou, Alejandro MousistHyperspectral Image Classification Hyperspectral Imaging
DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions
Jun 4, 2026Nathan Bout, Maxime Langevin, Ronan RiochetBenchmark Datasets Real-World Manipulation Tasks
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
Jun 4, 2026Gianluca Barmina, Peter Schneider-Kamp, Lukas Galke PoechMemorization Language Model Evasion Attacks
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
Jun 3, 2026Rishit Dagli, Abir Harrasse, Luke Zhang +4Training Data Attribution Training Data
Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
Jun 2, 2026Joanna Zou, Fraser Birks, Dallas Foster +1Interatomic Potentials Molecular Dynamics
KletterMix: Climbing Toward High-Quality German Pretraining Data
Jun 2, 2026Maurice Kraus, Ruben Härle, Sebastian Sztwiertnia +4Large Language Model Pretraining Text Corpora
Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillation
Jun 2, 2026Tianhe Wu, Zikai Zhou, Kun Yan +23Prompt Distillation Image Editing
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Jun 2, 2026Guhong Chen, Yingcheng Shi, Yongbin Li +6Agentic Reinforcement-Learning Framework Self-Evolving Agents
ROBUST-WT: Robust Uncertainty-aware Segmentation Transform via Whitening and Training Enhancements
Jun 2, 2026Aqsa Naseer, Maryam Bibi, Syeda Samiya Urooj +1Statistical Shape Model Cross-Entropy Losses
From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep Learning for Transferable Satellite-Derived Bathymetry
Jun 1, 2026Hsiao-Jou Hsu, Joachim MoortgatDeep Learning Ocean
HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
Jun 1, 2026Hezhen Hu, Wangbo Zhao, Lanqing Guo +6Animatable 3D Human Avatars High-Fidelity Avatar
A Primer in Post-Training Reasoning Data: What We Know About How It Works
Jun 1, 2026Yaoming Li, Guangxiang Zhao, Qilong Shi +3Table Reasoning Datasets LLM Post-Training Methods
HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
Jun 1, 2026Minghui Zheng, Hongxu Chen, Huimin Ren +8Large Language Model Compression Context Compression
BraveGuard: From Open-World Threats to Safer Computer-Use Agents
May 31, 2026Yunhao Feng, Xiaohu Du, Xinhao Deng +13Defense Strategies Threat Models
How (and when) can you fit examples to logic-based hypothesis classes over infinite structures?
May 31, 2026Michael Benedikt, Alessio MansuttiComputable Finite-Sample
Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers
May 30, 2026Yeqi Huang, Yue Chen, Yanwei Ye +2Biomedical Text Qwen3-Embedding-8B
Logit Distillation on Manifolds: Mapping by Learning
May 30, 2026Yiru Yang, Junling Wang, Nishant Kumar Singh +2Model Training Progressive Distillation
HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning
May 30, 2026Amir Hossein Shahdadian, Ahmed M. Abdelmoniem, Mahdi Taheri +2Heterogeneous Federated Learning Federated Learning

Jun 25, 2026 · cs.DCJ/K move · Enter open · S save

DMuon: Efficient Distributed Muon Training with Near-Adam Overhead

Vincent Chen, Starrick Liu, Regis Cheng, Dance Yang+7

X SQUARE ROBOT TEAM

Matrix-orthogonalization-based optimizers, exemplified by Muon, have demonstrated strong convergence behavior across a wide range of modern deep learning workloads. The matrix-aware updates offer a compelling alternative to conventional element-wise optimization, particularly as model architectures continue to grow in scale and heterogeneity. Yet contemporary distributed training infrastructure built around the assumption of element-wise optimizers is poorly matched to matrix-level optimizers such as Muon, whose updates couple entire weight matrices and require costly Newton-Schulz iterations. Vanilla Muon implementations incur more than 2x the cost of forward and backward passes. To close this gap, we present DMuon, an open-source distributed Muon implementation that integrates into existing training pipelines as a drop-in module, with no framework-level modifications. Across both embodied foundation model and large language model (LLM) training workloads, DMuon achieves a 1.48x-3.01x speedup in end-to-end step time and a 6.85x-163.00x speedup in optimizer-step time, bringing per-step latency to near-AdamW levels and enabling efficient scaling in our model training.

Muon Optimizer Muon Inference Workloads Model Training Low-Latency Systems High Inference Cost

Open paper Ask about it PDF