Feng Yang
6 أوراق في مجموعة PaperMetrix
أوراق هذا المؤلف
-
The Design of Self-purchasing System for Train Tickets Based on Block Chain Identity Authentication Technology
2018 · International Journal of Sciences
As a frontier technology, block chain has great prospects in the fields of internet of things and finance field. In the process of bitcoin transaction, the legality authentication of identity information is realized through block …
-
Method of Interaction between Blockchain and the World outside the Chain based on Oracle Machine
2022
Blockchain is a decentralized distributed ledger where data is produced and stored in units of blocks, and is connected end to end in chronological order to form a chain structure. However, at present, the blockchain …
-
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
2024 · arXiv (Cornell University)
Large Language Models (LLMs) sometimes suffer from producing hallucinations, especially LLMs may generate untruthful responses despite knowing the correct knowledge. Activating the truthfulness within LLM is the key to fully unlocking LLM's knowledge potential. In …
-
Learnable Privacy Neurons Localization in Language Models
2024
Concerns regarding Large Language Models (LLMs) to memorize and disclose private information, particularly Personally Identifiable Information (PII), become prominent within the community.Many efforts have been made to mitigate the privacy risks.However, the mechanism through which …
-
RCEFL: Reputation-based Communication-aware Optimization of Federated Learning
2024
Federated learning (FL) is a privacy-preserving distributed machine learning paradigm, where multiple devices holding local datasets collaborate to train a general global model without disclosing data. Instead of submitting raw data as in centralized training, …
-
Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contamination
2025 · arXiv (Cornell University)
Representation-based multi-task learning (MTL) improves efficiency by learning a shared structure across tasks, but its practical application is often hindered by contamination, outliers, or adversarial tasks. Most existing methods and theories assume a clean or …