machine learning

790 items

RESEARCHarXiv CS.LG·18d ago

A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction

This study introduces yvsoucom-iterkit, a deterministic and log-driven automated machine learning framework for interpretable pipeline optimization in healthcare risk prediction. It enables reproducible analysis of pipeline components, revealing that performance is driven by a small subset of interacting elements like augmentation, model choice, and imbalance handling.

Healthcare machine learning interpretability AutoML

RESEARCHarXiv CS.AI·5/11/2026

Weblica: Scalable and Reproducible Training Environments for Visual Web Agents

This paper introduces Weblica, a framework designed to construct reproducible and scalable web environments for visual web agents. It utilizes HTTP-level caching and LLM-based environment synthesis to scale RL training across thousands of diverse environments and tasks, outperforming baselines on web navigation benchmarks.

scalability reinforcement learning machine learning AI agents

RESEARCHarXiv CS.LG·27d ago

scShapeBench: Discovering geometry from high dimensional scRNAseq data

scShapeBench is a tool designed to discover geometry from high-dimensional single-cell RNA sequencing data, which is crucial for extracting biological information. It aims to automate shape detection, addressing the current reliance on manual visual inspection by bioinformaticians to select appropriate analysis pipelines.

single-cell RNAseq computational biology machine learning data analysis

RESEARCHarXiv CS.LG·23d ago

Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation

This paper introduces Mask-Morph Graph U-Net (MMGUNet), a practical approach addressing the limitation of hierarchical Graph U-Net architectures in crash simulations. It aims to improve generalisability by retaining fixed coarse graph connectivity while improving spatial correspondence, offering a faster alternative to computationally expensive finite element methods.

Surrogate Models Crashworthiness Graph Neural Networks machine learning

RESEARCHarXiv CS.CL·23d ago

Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time

This research introduces OP-Mix, a novel algorithm for efficient data mixing throughout the entire lifecycle of language model training. It addresses the challenge of combining diverse data sources for pretraining, continual learning, and adaptation, proposing a unified online decision-making solution.

language models learning data mixing machine learning

RESEARCHarXiv CS.LG·18d ago

The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity

The paper proves that no feature ranking can be simultaneously faithful, stable, and complete when features are collinear, as ranking for collinear pairs reduces to a coin flip. It resolves this impossibility through ensemble averaging (DASH), characterizing the complete attribution design space and quantifying the problem for different model classes.

attribution ensemble methods feature ranking collinearity

RESEARCHarXiv CS.LG·5/11/2026

On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching

This paper analyzes the role of strain and vorticity in numerical integration error for flow matching, proving that strain controls exponential error amplification while vorticity contributes linearly. It further shows that optimal transport velocity fields are irrotational, leading to second-order Euler accuracy.

Numerical Methods machine learning AI Flow Matching

RESEARCHarXiv CS.CL·5/11/2026

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries

This paper introduces Group of Skills (GoSkills), an inference-time group-structured retrieval method for AI agent skill libraries. It transforms flat skill lists into compact, role-labeled execution contexts, building anchor-centered skill groups and rendering a fixed execution contract with Start, Support, Check, and Avoid fields.

Skill Retrieval machine learning Information Retrieval AI agents

RESEARCHarXiv CS.AI·28d ago

EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

EVOCHAMBER presents a training-free framework that instantiates test-time evolution at three levels over a coevolving agent pool, distinguishing it from single-agent approaches. It features CODREAM, a post-task protocol for collaborative reflection and asymmetric knowledge routing after team failures or disagreements.

Evolutionary AI machine learning multi-agent systems Collaboration

RESEARCHarXiv CS.LG·21d ago

Theory-optimal Quantization Based on Flatness

This research models the relationship between quantization error and outliers in Large Language Models (LLMs) and introduces a new metric, Flatness, to quantify outlier distribution. Based on this, it derives a theoretical optimal solution and proposes Bidirectional Diagonal Quantization (BDQ) for post-training quantization.

deep learning machine learning quantization AI

RESEARCHarXiv CS.LG·27d ago

Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic

This paper introduces Embedding Temporal Logic (ETL) for runtime monitoring of perception-based autonomous systems. ETL operates directly in learned embedding spaces, defining predicates through distances between observed and target embeddings to capture high-level perceptual concepts.

temporal logic Autonomous systems machine learning runtime monitoring

RESEARCHarXiv CS.CL·21d ago

The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints

Low-resource natural language processing has experienced explosive growth, but its evaluation faces a critical challenge: the scarcity of sociolinguistic expertise needed to assess complex generative systems. This creates an "Annotation Scarcity Paradox," where the technical capacity to scale models vastly outpaces the human infrastructure required for authentic evaluation.

machine learning NLP Low-resource languages AI evaluation

RESEARCHarXiv CS.CL·8d ago

AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection

This paper introduces AEyeDE, an attention-driven framework for human-AI authorship detection that leverages model attention as a discriminative signal. The method consistently outperforms text-only baselines and shows robustness across various text generation settings, remaining competitive on standard benchmarks.

AI detection machine learning NLP Attention Mechanisms

RESEARCHarXiv CS.AI·23d ago

NOVA: Fundamental Limits of Knowledge Discovery Through AI

The NOVA framework models AI knowledge discovery as an adaptive sampling process, identifying conditions for genuine knowledge accumulation and common failure modes like contamination and forgetting. It highlights a "contamination trap" where invalid artifacts can accumulate faster than genuine discoveries as easy-to-find knowledge is exhausted, even with small false-positive rates.

research machine learning AI Knowledge Discovery

RESEARCHarXiv CS.LG·27d ago

Multi-Rollout On-Policy Distillation via Peer Successes and Failures

The paper introduces Multi-Rollout On-Policy Distillation (MOPD), a framework that uses a student's local rollout group to construct more informative teacher signals for post-training large language models. MOPD conditions the teacher on both successful and failed peer rollouts, leveraging successes for valid reasoning patterns and failures for avoiding plausible mistakes.

distillation reinforcement learning AI Training machine learning

RESEARCHarXiv CS.CL·28d ago

Decomposing Evolutionary Mixture-of-LoRA Architectures: The Routing Lever, the Lifecycle Penalty, and a Substrate-Conditional Boundary

This paper decomposes an evolutionary Mixture-of-LoRA system, examining factors such as router rewrite, per-domain evaluation, and an adaptation lifecycle. Results indicate that the router rewrite is solely responsible for the balanced log-PPL improvement observed.

neural networks machine learning large language models LoRA

RESEARCHarXiv CS.LG·27d ago

Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance

This paper introduces a communication-efficient reinforcement learning approach where a single policy learns both control inputs and timing decisions, secured by a pointwise Lyapunov safety shield. A run-time assurance layer overrides the policy to provide strictly stronger safety guarantees and achieve significantly higher mean inter-sample intervals on various systems.

reinforcement learning machine learning safety-critical-ai Control Systems

RESEARCHarXiv CS.CL·23d ago

Automatic Construction of a Legal Citation Graph from 100 Million Ukrainian Court Decisions: Large-Scale Extraction, Topological Analysis, and Ontology-Driven Clustering

This study details the automatic construction of a legal citation graph from 100 million Ukrainian court decisions. The analysis reveals that judicial citation structure encodes legal domain boundaries and predicts future legislative importance with high accuracy.

LegalTech machine learning data science AI

RESEARCHarXiv CS.LG·28d ago

Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization

The paper introduces Vertex-Softmax, a novel method for certified verification of transformer attention by exactly optimizing the softmax function. It proves that the exact optimum is attained at a vertex of the constraint box, yielding a tighter sound bound.

Optimization machine learning Verification AI

RESEARCHarXiv CS.LG·28d ago

QuIDE: Mastering the Quantized Intelligence Trade-off via Active Optimization

QuIDE introduces a unified metric, the Intelligence Index I, to evaluate the efficiency of quantized neural networks by collapsing the compression-accuracy-latency trade-off. Experiments across various settings identify task-dependent optimal quantization (4-bit or 8-bit), providing a reproducible evaluation protocol and a fitness function for mixed-precision search.

neural networks Optimization machine learning AI Efficiency