Chong Wang

Agile Practitioners’ Understanding of Security Requirements: Insights from a Grounded Theory Analysis

2017

A 2017 systematic review on engineering non-functional requirements in agile projects revealed a number of published proposals for approaching security requirements in agile settings. While these proposals acknowledge the urgent need for methods to systematically …

Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference

2019 · arXiv (Cornell University)

Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture …

Learning An End-to-End Structure for Retrieval in Large-Scale Recommendations

2021

One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an inner-product model, …

AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations

2021

Deep learning-based recommender systems (DLRSs) often have embedding layers, which are utilized to lessen the dimension of categorical variables (e.g., user/item identifiers) and meaningfully transform them in the low-dimensional space. The majority of existing DLRSs …

Feature Differentiation Reconstruction Network for Weakly-Supervised Video Anomaly Detection

2023 · IEEE Signal Processing Letters

Recent research into video anomaly detection under weakly supervised settings has made significant progress in identifying anomalies with only coarse-grained annotations. Mainstream weakly supervised methods improve detection performance by generating high-quality pseudo labels for video …

A Vision for Auto Research with LLM Agents

2025 · arXiv (Cornell University)

This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Leveraging the capabilities of large language models (LLMs) and modular agent collaboration, the …

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

2015 · arXiv (Cornell University)

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning …