Hugging Face Trending Papers July 8, 2026

Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives

Read the original on Hugging Face Trending Papers →

Modern machine learning (ML) increasingly relies on complex models whose behavior is difficult to characterize beyond empirical performance metrics. Across a wide range of tasks, including prediction, generation, and decision-making, models with similar empirical performance can exhibit markedly different properties in terms of their transparency, interpretability, robustness, fairness, privacy, and certifiability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jul 10

Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives

arXiv:2607. 07762v1 Announce Type: new Abstract: Modern machine learning (ML) increasingly relies on complex models whose behavior is difficult to characterize beyond empirical performance metrics.

By Thibaut Vidal, Julien Ferry

efficiency safety

arXiv Machine Learning

Sep 1

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

arXiv:2608.28934v1 Announce Type: new Abstract: Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In...

By Saloni Modi, Srivi Balaji, Yusong Zhu, Gautam Kamath, Kevin Tian

benchmarks safety

arXiv Machine Learning

Jul 27

Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification

arXiv:2607. 21839v1 Announce Type: cross Abstract: Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training data.

By Carter Luck, Olive Franzese-McLaughlin, Elisaweta Masserova, Akira Takahashi, Antigoni Polychroniadou, Nicolas Papernot

safety

arXiv AI

Jun 24

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.

By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud

llms benchmarks safety

arXiv Machine Learning

Jul 1

Efficient Public Verification of Private ML via Regularization

arXiv:2512. 04008v2 Announce Type: replace Abstract: Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model.

By Zo\"e Ruha Bell, Anvith Thudi, Olive Franzese-McLaughlin, Nicolas Papernot, Shafi Goldwasser

safety

arXiv AI

Jun 2

Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution

arXiv:2605. 02640v2 Announce Type: replace Abstract: As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), are increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge.

By Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Sch\"olkopf, Mario Fritz

safety

One email a morning, machine-written

Related stories

Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

Efficient Public Verification of Private ML via Regularization

Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution