Related papers: Type4Py: Practical Deep Similarity Learning-Based …

With the rise of software-as-a-service and microservice architectures, RESTful APIs are now ubiquitous in mobile and web applications. A service can have tens or hundreds of API methods, making it a challenge for programmers to find the…

Many important security properties can be formulated in terms of flows of tainted data, and improved taint analysis tools to prevent such flows are of critical need. Most existing taint analyses use whole-program static analysis, leading to…

Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that…

The P4 programming language offers high-level, declarative abstractions that bring the flexibility of software to the domain of networking. Unfortunately, the main abstraction used to represent packet data in P4, namely header types, lacks…

Current systems of fine-grained entity typing use distant supervision in conjunction with existing knowledge bases to assign categories (type labels) to entity mentions. However, the type labels so obtained from knowledge bases are often…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

Current state-of-the-art solvers for mixed-integer programming (MIP) problems are designed to perform well on a wide range of problems. However, for many real-world use cases, problem instances come from a narrow distribution. This has…

The development of largely human-annotated benchmarks has driven the success of deep neural networks in various NLP tasks. To enhance the effectiveness of existing benchmarks, collecting new additional input-output pairs is often too costly…

This work revisits and extends synthetic query generation pipelines for Neural Information Retrieval (NIR) by leveraging the InPars Toolkit, a reproducible, end-to-end framework for generating training data using large language models…

For continual learning, text-prompt-based methods leverage text encoders and learnable prompts to encode semantic features for sequentially arrived classes over time. A common challenge encountered by existing works is how to learn unique…

Dynamically typed programming languages are popular in education and the software industry. While presenting a low barrier to entry, they suffer from run-time type errors and longer-term problems in code quality and maintainability.…

Prototype learning, a popular machine learning method designed for inherently interpretable decisions, leverages similarities to learned prototypes for classifying new data. While it is mainly applied in computer vision, in this work, we…

PyPM is a Python-based domain specific language (DSL) for building rewrite-based optimization passes on machine learning computation graphs. Users define individual optimizations by writing (a) patterns that match subgraphs of a computation…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Search-augmented large language models (LLMs) trained with reinforcement learning (RL) have achieved strong results on open-domain question answering (QA), but training still remains a significant challenge. The optimization is often…

Inference algorithms in probabilistic programming languages (PPLs) can be thought of as interpreters, since an inference algorithm traverses a model given evidence to answer a query. As with interpreters, we can improve the efficiency of…

For the task of fine-grained entity typing (FET), due to the use of a large number of entity types, it is usually considered too costly to manually annotating a training dataset that contains an ample number of examples for each type. A…

Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational costs and even degrade performance. Inspired by human…

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…