ArXiv TLDR
← All categories

Machine Learning

Papers on learning algorithms, neural networks, deep learning, and optimization.

cs.LG · 1353 papers

Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter Matching

This paper compares dense and MoE transformers at tiny scale, finding MoE outperforms dense when matching active parameters but not total parameters.

2605.13769May 13, 2026Abdalrahman Wael

High-Rate Quantized Matrix Multiplication II

This paper explores high-rate quantized matrix multiplication for LLMs, showing how waterfilling improves GPTQ and analyzing the near-optimal WaterSIC scheme.

2605.13768May 13, 2026Or Ordentlich, Yury Polyanskiy

VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense

VectorSmuggle reveals steganographic data exfiltration in RAG embedding stores and proposes VectorPin, a cryptographic defense for embedding integrity.

2605.13764May 13, 2026Jascha Wanger

Min Generalized Sliced Gromov Wasserstein: A Scalable Path to Gromov Wasserstein

min-GSGW offers a scalable, rigid-motion invariant method for Gromov-Wasserstein by using generalized slicers and an amortized variant.

2605.13753May 13, 2026Ashkan Shahbazi, Xinran Liu, Ping He +1

Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography

An explainable AI model accurately diagnoses bicuspid aortic valve (BAV) from tricuspid aortic valve (TAV) using routine echocardiography.

2605.13730May 13, 2026Christos Chrysanthos Nikolaidis, Vasileios Sachpekidis, Nikolas Moustakidis +2

Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety

Fine-tuning compact 8B LLMs with expert curricula generates children's English stories with controllable difficulty and safety, outperforming larger models.

2605.13709May 13, 2026Qian Shen, Fanghua Cao, Min Yao +3

DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning

DisAgg uses distributed client aggregators to securely and efficiently aggregate updates in federated learning, achieving a 4.6x speedup over OPA.

2605.13708May 13, 2026Haaris Mehmood, Giorgos Tatsis, Dimitrios Alexopoulos +4

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training

Low-rank pre-training methods yield geometrically distinct solutions from full-rank models and each other, even with similar perplexity, requiring deeper evaluation metrics.

2605.13652May 13, 2026Namrata Shivagunde, Vijeta Deshpande, Sherin Muckatira +1

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization

RDPO improves multi-objective and mixed-reward RL by decorrelating rewards and stabilizing advantage allocation for diverse reward types.

2605.13641May 13, 2026Yang Bai, Kaiyuan Liu, Ziyuan Zhuang +5

RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation

RealICU is a new benchmark for evaluating LLM agents on long-context ICU data, revealing recall-safety tradeoffs and anchoring biases in existing models.

2605.13542May 13, 2026Chengzhi Shen, Weixiang Shen, Tobias Susetzky +8

Limits of Personalizing Differential Privacy Budgets

This paper reveals that personalized differential privacy budgets have significant limitations, showing a simple thresholding method is often superior.

2605.13503May 13, 2026Edwige Cyffers, Juba Ziani

Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling

Smart-SIEM enhances open-source SIEMs with an AI module for context-aware web attack detection using behavioral profiling and MITRE ATT&CK.

2605.13337May 13, 2026Badr Alboushy, Assef Jafar, Mohamad Aljnidi +2

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks

This paper shows how to create cryptographically undetectable backdoors in modern neural networks by exploiting latent space geometry, resisting current defenses.

2605.13214May 13, 2026Marte Eggen, Eirik Reiestad, Kristian Gjøsteen +1

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters

LoREnc is a training-free framework that secures foundation models and LoRA adapters against IP leakage and model recovery attacks with minimal overhead.

2605.13163May 13, 2026Beomjin Ahn, Jungmin Kwon, Chanyong Jung +1

Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study

This study finds code language models struggle to detect vulnerability-fixing commits without commit messages, lacking transferable security understanding from code changes alone.

2605.13138May 13, 2026Nils Loose, Joseph Bienhüls, Kristoffer Hempel +2

Protocol-Driven Development: Governing Generated Software Through Invariants and Evidence

Protocol-Driven Development (PDD) governs generated software by using machine-enforceable protocols, invariants, and verifiable evidence chains.

2605.12981May 13, 2026Jun He, Deying Yu

A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data

RSNet is an R package for robust, interpretable network inference in high-dimensional data, using resampling and graphlet analysis for structural insights.

2605.12706May 12, 2026Ziwei Huang, Zeyuan Song, Paola Sebastiani +1

scShapeBench: Discovering geometry from high dimensional scRNAseq data

scShapeBench introduces a benchmark and scReebTower, a new method for automated shape detection in high-dimensional scRNAseq data, outperforming baselines.

2605.12662May 12, 2026Andrew J Steindl, João Felipe Rocha, Brian Tshilengi Di Bassinga +13

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

AlphaGRPO enhances multimodal generation in UMMs using GRPO and a novel Decompositional Verifiable Reward for self-reflection and reasoning.

2605.12495May 12, 2026Runhui Huang, Jie Wu, Rui Yang +2

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

Pion is a novel spectrum-preserving optimizer for LLMs that uses orthogonal transformations to maintain singular values throughout training.

2605.12492May 12, 2026Kexuan Shi, Hanxuan Li, Zeju Qiu +3
PreviousPage 2 of 68Next

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.