Yulong Wang

U-TRI

2017

Traffic analysis within switches is threatening the security of large enterprise networks built with SDN. Adversaries are able to monitor all traffic traversing a switch by exploiting just one vulnerability in it and obtain linkage …

Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese

2021 · arXiv (Cornell University)

Although pre-trained models (PLMs) have achieved remarkable improvements in a wide range of NLP tasks, they are expensive in terms of time and resources. This calls for the study of training more efficient models with …

Feature-opinion pair identification method in two-stage based on dependency constraints

2018 · International Journal of Information and Communication Technology

Feature-opinion pair identification includes opinion words, opinion targets extraction and their relations identification, is important for analysis online reviews. In this paper, we propose a feature-opinion pair identification method in two-stage based on dependency constraints …

Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning

2024 · arXiv (Cornell University)

Existing agents based on large language models (LLMs) demonstrate robust problem-solving capabilities by integrating LLMs' inherent knowledge, strong in-context learning and zero-shot capabilities, and the use of tools combined with intricately designed LLM invocation workflows …

Linear Chain Transformation: Expanding Optimization Dynamics for Fine-Tuning Large Language Models

2024 · arXiv (Cornell University)

Fine-tuning large language models (LLMs) has become essential for adapting pretrained models to specific downstream tasks. In this paper, we propose Linear Chain Transformation (LinChain), a novel approach that introduces a sequence of linear transformations …