Advanced Data Processing Techniques

Latest papers

• Fuzzy Segmentations of a String

  Armen Kostanyan, Arevik Harmandayan · 26 August 2026

  This article discusses a particular case of the data clustering problem, where it is necessary to find groups of adjacent text segments of the appropriate length that match a fuzzy pattern represented as a sequence of fuzzy properties. To solve this problem, a heuristic algorithm for finding a suffi…

• MLCC: A Congestion Control Technique to Accelerate ML Training

  Anton A. Zabreyko, Sanjoli Narang, Sudarsanan Rajasekaran, Manya Ghobadi · 17 August 2026

  We present MLCC, a novel technique to augment today's congestion control algorithms to accelerate DNN training jobs in shared GPU clusters in a fully distributed manner. At the heart of MLCC lies a straightforward principle: DNN training flows should scale their sending rate to shift other flows' co…

• Deep Learning Alternatives of the Kolmogorov Superposition Theorem

  Leonardo Ferreira Guilhoto, Paris Perdikaris · 18 May 2026

  This paper explores alternative formulations of the Kolmogorov Superposition Theorem (KST) as a foundation for neural network design. The original KST formulation, while mathematically elegant, presents practical challenges due to its limited insight into the structure of inner and outer functions a…

• Automatic Construction of Pattern Classifiers Capable of Continuous Incremental Learning and Unlearning Tasks Based on Compact-Sized Probabilistic Neural Network

  Tetsuya Hoya, Shunpei Morita · 24 March 2026

  This paper proposes a novel approach to pattern classification using a probabilistic neural network model. The strategy is based on a compact-sized probabilistic neural network capable of continuous incremental learning and unlearning tasks. The network is constructed/reconstructed using a simple, o…

• LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed

  Chang Yang, Xinrun Wang, Junzhe Jiang, Qinggang Zhang, Xiao Huang · 20 March 2026

  World model emerges as a key module in decision making, where MuZero and Dreamer achieve remarkable successes in complex tasks. Recent work leverages Large Language Models (LLMs) as general world simulators to simulate the dynamics of the world due to their generalizability. LLMs also serve as the w…

• MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training

  Juntao Zhao, Qi Lu, Wei Jia, Borui Wan, Lei Zuo, Junda Feng, Jianyu Jiang, Yangrui Chen, Shuaishuai Cao, Jialing He, Kaihua Jiang, Yuanzhe Hu, Shibiao Nong, Yanghua Peng, Haibin Lin, Chuan Wu · 17 March 2026

  Modern frameworks for training large foundation models (LFMs) employ dataloaders in a data-parallel manner, with each loader processing a disjoint subset of training data. When preparing data for LFM training that originates from multiple, distinct sources, two fundamental challenges arise. First, d…

• Large Language Model Integration with Reinforcement Learning to Augment Decision-Making in Autonomous Cyber Operations

  Konur Tholl, Fran\c{c}ois Rivest, Mariam El Mezouar, Adrian Taylor, Ranwa Al Mallah · 17 February 2026

  Reinforcement Learning (RL) has shown great potential for autonomous decision-making in the cybersecurity domain, enabling agents to learn through direct environment interaction. However, RL agents in Autonomous Cyber Operations (ACO) typically learn from scratch, requiring them to execute undesirab…

• Batch-CAM: Introduction to better reasoning in convolutional deep learning models

  Giacomo Ignesti, Davide Moroni, Massimo Martinelli · 16 February 2026

  Deep learning opacity often impedes deployment in high-stakes domains. We propose a training framework that aligns model focus with class-representative features without requiring pixel-level annotations. To this end, we introduce Batch-CAM, a vectorised implementation of Gradient-weighted Class Act…

• EXAONE 3.0 7.8B Instruction Tuned Language Model

  Soyoung An, Kyunghoon Bae, Eunbi Choi, Stanley Jungkyu Choi, Yemuk Choi, Seokhee Hong, Yeonjung Hong, Junwon Hwang, Hyojin Jeon, Gerrard Jeongwon Jo, Hyunjik Jo, Jiyeon Jung, Yountae Jung, Euisoon Kim, Hyosang Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Youchul Kim, Edward Hwayoung Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Lee, Moontae Lee, Seungjun Lee, Woohyung Lim, Sangha Park, Sooyoun Park, Yongmin Park, Boseong Seo, Sihoon Yang, Heuiyeen Yeen, Kyungjae Yoo, Hyeongu Yun · 5 January 2026

  We introduce EXAONE 3.0 instruction-tuned language model, the first open model in the family of Large Language Models (LLMs) developed by LG AI Research. Among different model sizes, we publicly release the 7.8B instruction-tuned model to promote open research and innovations. Through extensive eval…

• Logarithmic Regret of Exploration in Average Reward Markov Decision Processes

  Victor Boone, Bruno Gaujal · 1 December 2025

  In average reward Markov decision processes, state-of-the-art algorithms for regret minimization follow a well-established framework: They are model-based, optimistic and episodic. First, they maintain a confidence region from which optimistic policies are computed using a well-known subroutine call…

• Physics-Informed Latent Neural Operator for Real-time Predictions of time-dependent parametric PDEs

  Sharmila Karumuri, Lori Graham-Brady, Somdatta Goswami · 29 October 2025

  Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings aris…