A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
A privacy-preserving FCNN framework using TFHE-based inference for secure medical image analysis on MedMNIST.
Unknown
HT2ML combines homomorphic encryption and trusted execution environments to enable efficient privacy-preserving machine learning on outsourced cloud data.
Rahul Rachuri, Ajith Suresh
Trident presents an efficient four-party framework for privacy-preserving machine learning, introducing specialized conversions for secure computation.
Unknown
Proposes PFMLP, a multi-party privacy-preserving machine learning framework combining partially homomorphic encryption with federated learning.
Unknown
LLM-Evolve introduces a multi-round evaluation framework to assess how LLMs' capabilities evolve across repeated benchmark interactions.
Unknown
This paper explores the instability of the ELO method in LLM evaluation and proposes a stable framework for arena-based evaluation.
Unknown
OFMU frames machine unlearning as an optimization problem where forgetting is a non-negotiable constraint, ensuring target data influence is fully removed.
Unknown
The paper introduces corrective machine unlearning, a framework for updating models to remove or correct harmful data points without full retraining.
Unknown
A statistical and approximation theory framework predicting neural scaling laws for transformers on intrinsically low-dimensional data, quantifying data and model scaling exponents.
Unknown
The paper proposes a probabilistic framework to characterize LLM agents by their values and understanding, and investigates whether they exhibit social behavior in laboratory experiments.
Unknown
AgentSpec introduces a customizable runtime enforcement framework for safe and reliable LLM agents, formalizing agents and enabling user-defined safety constraints.
Unknown
Proposes GRACEs, a principled framework for selecting optimal teacher language models to improve knowledge distillation into smaller student models.