Machine Learning

cs.LGComputer Science60 papers

Every entry carries a structured overview and the reproduction evidence collected so far. A paper is listed here when it carries the category as its primary field or as a secondary classification. Both are shown on the paper page.

Latest in cs.LG

Showing 1–20 of 60

Apr 25, 2026cs.LG260425.0003

Bayesian Optimization: A Pure-Python Sequential Model-Based Optimization Library

Authors pending

Bayesian optimization via Gaussian Process surrogate — installs with pip install bayesian-optimization, runs in <5s with no GPU.

Reference implementationRuns97% match · pre-ledger4 attempts

Apr 25, 2026cs.LG260425.0002

Fundamental Machine Learning Algorithms Implemented from Scratch in Python

Authors pending

A from-scratch NumPy implementation of 20+ ML algorithms with runnable example scripts.

Reference implementationRuns3 attempts

Apr 25, 2026cs.LG260425.0001

micrograd: A tiny scalar-valued autograd engine and neural net library

Authors pending

micrograd is a ~200-line pure-Python autograd engine + neural net library that backpropagates through scalar operations.

Reference implementationRuns40% match · pre-ledger4 attempts

Apr 22, 2026Formal Sciences260423.0001

FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels

Sina Gholami, Abdulmoneam Ali, Tania Haghighi, Ahmed Arafa +1 more

FedSIR is a federated learning framework that identifies noisy labels and clients by analyzing spectral properties of feature representations, then uses clean clients to help relabel corrupted samples. The method combines spectral analysis with noise-aware training strategies to achieve robust collaborative learning despite label noise.

CodeRun failed1 attempt

Apr 22, 2026Formal Sciences260423.0002

Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples

Ana Sanchez-Fernandez, Thomas Pinetz, Werner Zellinger, Günter Klambauer

This paper proposes CS-ARM-BN, a meta-learning method that uses negative control samples to adapt deep learning models to new experimental batches in biomedical imaging, closing the domain gap caused by batch effects. The approach achieves 0.935±0.018 accuracy on drug mechanism-of-action classification, recovering performance from 0.862±0.060 back to near training-domain levels of 0.939±0.005.

Apr 22, 2026Formal Sciences260423.0004

Stream-CQSA: Avoiding Out-of-Memory in Attention Computation via Flexible Workload Scheduling

Yiming Bian, Joshua M. Akey

Stream-CQSA enables exact self-attention computation on long sequences by decomposing attention into independent subsequence computations that fit within arbitrary memory budgets, allowing billion-token sequences to run on a single GPU without approximation. This removes the assumption that full query, key, and value tensors must fit in device memory, addressing the quadratic memory bottleneck of standard attention.

Apr 22, 2026Formal Sciences260423.0008

Physics-Conditioned Synthesis of Internal Ice-Layer Thickness for Incomplete Layer Traces

Zesheng Liu, Maryam Rahnemoonfar

This paper develops a physics-conditioned neural network to complete incomplete ice-layer thickness measurements from radar data by synthesizing missing layer traces. The approach combines geometric and temporal learning with physical climate model features to recover fragmented or absent layers while maintaining consistency with observed data.

Apr 22, 2026Formal Sciences260423.0009

Efficient Multi-Cohort Inference for Long-Term Effects and Lifetime Value in A/B Testing with User Learning

Dario Simionato, Andrea Tonon, Mingxue Wang, Weiguo Wang +2 more

This paper proposes a method to estimate long-term treatment effects and lifetime value changes in A/B tests for streaming platforms where user churn is costly. It uses inverse-variance weighted estimation across multiple cohorts and parametric decay modeling to capture both steady-state impact and cumulative user value within short experiments.

Apr 22, 2026Formal Sciences260423.0013

Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems

Beining Wu, Jun Huang

This paper proposes a lifecycle-aware federated continual learning framework for distributed autonomous fleets that addresses both immediate forgetting during training and long-term cumulative drift through layer-selective rehearsal and rapid recovery strategies. The approach is validated theoretically and empirically, including on a real rover testbed.

Apr 22, 2026Formal Sciences260423.0015

F\textsuperscript{2}LP-AP: Fast \& Flexible Label Propagation with Adaptive Propagation Kernel

Yutong Shen, Ruizhe Xia, Jingyi Liu, Yinqi Liu

F²LP-AP is a training-free label propagation method that adapts to both homophilous and heterophilous graphs using geometric median prototypes and local clustering coefficients. It achieves competitive accuracy with GNNs while being significantly more computationally efficient.

Apr 22, 2026Formal Sciences260423.0016

Fast Bayesian equipment condition monitoring via simulation based inference: applications to heat exchanger health

Peter Collett, Alexander Johannes Stasik, Simone Casolo, Signe Riemer-Sørensen

This paper proposes a Simulation-Based Inference (SBI) framework using neural networks for fast Bayesian condition monitoring of industrial equipment, specifically heat exchangers. The approach achieves 82× speedup over MCMC while maintaining comparable diagnostic accuracy and uncertainty quantification.

Apr 22, 2026Formal Sciences260423.0017

Near-Future Policy Optimization

Chuanyu Qin, Chenxu Yang, Qingyi Si, Naibin Gu +5 more

Near-Future Policy Optimization (NPO) improves reinforcement learning with verifiable rewards by learning from a policy's own future checkpoints, which are both higher quality and closer to the current policy than external sources. The method achieves significant performance gains on vision-language models, improving from 57.88 to 63.15 on Qwen3-VL-8B-Instruct.

Apr 22, 2026Formal Sciences260423.0018

Supplement Generation Training for Enhancing Agentic Task Performance

Young Min Cho, Daniele Bonadiman, Divya Bhargavi, Tamer Alkhouli +7 more

The paper proposes Supplement Generation Training (SGT), which trains smaller LLMs to generate supplemental text that improves larger foundation models' performance on agentic tasks without retraining the large models. This approach reduces computational costs and enables efficient adaptation to new tasks and domains.

Apr 22, 2026Formal Sciences260423.0019

Tokenised Flow Matching for Hierarchical Simulation Based Inference

Giovanni Charles, Cosmo Santoni, Seth Flaxman, Elizaveta Semenova

This paper proposes Tokenised Flow Matching for Posterior Estimation (TFMPE), a method that reduces simulator evaluation costs in hierarchical simulation-based inference by learning per-site neural surrogates and assembling synthetic observations. The approach is validated on infectious disease and computational fluid dynamics models with improved computational efficiency.

Apr 22, 2026Formal Sciences260423.0020

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling

Noah Flynn

COMPASS is a data-centric framework that adapts large language models to target languages using parameter-efficient fine-tuning with semantic-aware sampling of multilingual data. It minimizes negative cross-lingual interference while maximizing positive transfer, and includes a continual learning variant to handle production data distribution shifts.

Apr 22, 2026Formal Sciences260423.0021

Generative Flow Networks for Model Adaptation in Digital Twins of Natural Systems

Pascal Archambault, Houari Sahraoui, Eugene Syriani

This paper applies Generative Flow Networks (GFlowNets) to adapt digital twin models of natural systems by learning to sample simulator parameters proportional to their agreement with observations. The approach handles the fundamental challenge that sparse observations often leave multiple plausible parameter configurations, preserving uncertainty rather than finding a single optimal solution.

Apr 22, 2026Formal Sciences260423.0023

MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment

Andor Vári-Kakas, Ji Won Park, Natasa Tagasovska

MGDA-Decoupled is a geometry-based multi-objective optimization algorithm for aligning LLMs that balances conflicting objectives like helpfulness and truthfulness without requiring reinforcement learning or explicit reward models. It operates within the Direct Preference Optimization framework and achieves higher win rates than existing methods by accounting for each objective's convergence dynamics.

Apr 22, 2026Formal Sciences260423.0024

Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales

Samuel Salfati

This paper systematically studies transformer compression across GPT-2 and Mistral 7B, identifying five structural properties that explain why certain compression techniques fail, particularly showing that high-variance activations are not predictively important and that block-level approximations suffer from distribution shift. The findings suggest fundamental limits to static compression and motivate adaptive, per-token approaches instead.

Apr 22, 2026Formal Sciences260423.0025

Improving clinical interpretability of linear neuroimaging models through feature whitening

Sara Petiton, Antoine Grigis, Raphaël Vock, Edouard Duchesnay

This paper proposes a feature whitening approach that decorrelates anatomically grouped brain regions to improve the interpretability of linear neuroimaging models while maintaining predictive performance. The method helps disentangle overlapping information across correlated brain measures, making model weights more clinically meaningful for identifying biomarkers in psychiatric disorders.

Apr 22, 2026Formal Sciences260423.0026

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning

Jingyi Wang, Lei Zhu, Tengjin Weng, Song-Li Wu +7 more

This paper introduces GRPO-VPS, which enhances Group Relative Policy Optimization by adding verifiable process supervision that tracks the model's confidence in correct answers throughout reasoning steps. This enables more targeted credit assignment and sample-efficient policy updates without requiring critic models or auxiliary supervision.

Machine Learning

Latest in cs.LG

Bayesian Optimization: A Pure-Python Sequential Model-Based Optimization Library

Fundamental Machine Learning Algorithms Implemented from Scratch in Python

micrograd: A tiny scalar-valued autograd engine and neural net library

FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels

Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples

Stream-CQSA: Avoiding Out-of-Memory in Attention Computation via Flexible Workload Scheduling

Physics-Conditioned Synthesis of Internal Ice-Layer Thickness for Incomplete Layer Traces

Efficient Multi-Cohort Inference for Long-Term Effects and Lifetime Value in A/B Testing with User Learning

Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems

F\textsuperscript{2}LP-AP: Fast \& Flexible Label Propagation with Adaptive Propagation Kernel

Fast Bayesian equipment condition monitoring via simulation based inference: applications to heat exchanger health

Near-Future Policy Optimization

Supplement Generation Training for Enhancing Agentic Task Performance

Tokenised Flow Matching for Hierarchical Simulation Based Inference

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling

Generative Flow Networks for Model Adaptation in Digital Twins of Natural Systems

MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment

Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales

Improving clinical interpretability of linear neuroimaging models through feature whitening

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning

Follow