Peng Sun

Mining Specifications from Documentation using a Crowd

2019

Temporal API specifications are useful for many software engineering tasks, such as test case generation. In practice, however, APIs are rarely formally specified, inspiring researchers to develop tools that infer or mine specifications automatically.Traditional specification …

Reinforcement Learning Recommendation Algorithm Based on Label Value Distribution

2023 · Mathematics

Reinforcement learning is an important machine learning method and has become a hot popular research direction topic at present in recent years. The combination of reinforcement learning and a recommendation system, is a very important …

A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives

2023 · arXiv (Cornell University)

Backdoor attacks pose serious security threats to deep neural networks (DNNs). Backdoored models make arbitrarily (targeted) incorrect predictions on inputs embedded with well-designed triggers while behaving normally on clean inputs. Many works have explored the …

A new feature extraction method for short wave signal

2023

Shortwave signal type recognition plays a very important role in the field of non-cooperative communication, but because of the low signal-to-noise ratio of the shortwave channel, it is often very difficult to identify the shortwave …

Efficiency for Free: Ideal Data Are Transportable Representations

2024 · arXiv (Cornell University)

Data, the seminal opportunity and challenge in modern machine learning, currently constrains the scalability of representation learning and impedes the pace of model evolution. In this work, we investigate the efficiency properties of data from …

LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism

2024

The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request. Restricted by static …

ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation

2021 · arXiv (Cornell University)

Pre-trained models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. Recent works such as T5 and GPT-3 have shown that scaling up pre-trained language models can improve their generalization abilities. Particularly, the …