Related papers: Compiling Gradual Types with Evidence
The generation of realistic and contextually relevant co-speech gestures is a challenging yet increasingly important task in the creation of multimodal artificial agents. Prior methods focused on learning a direct correspondence between…
We present a type system and inference algorithm for a rich subset of JavaScript equipped with objects, structural subtyping, prototype inheritance, and first-class methods. The type system supports abstract and recursive objects, and is…
Modern Just-in-Time compilers (or JITs) typically interleave several mechanisms to execute a program. For faster startup times and to observe the initial behavior of an execution, interpretation can be initially used. But after a while,…
Large language models (LLMs) have demonstrated strong performance in natural language generation but remain limited in knowle- dge-intensive tasks due to outdated or incomplete internal knowledge. Retrieval-Augmented Generation (RAG)…
Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable generalization capabilities to downstream tasks. However, existing prompt tuning based frameworks need to parallelize learnable textual inputs for all categories,…
Data engineering pipelines are essential - albeit costly - components of predictive analytics frameworks requiring significant engineering time and domain expertise for carrying out tasks such as data ingestion, preprocessing, feature…
This study explores the problem solving capabilities of ChatGPT and its prospective applications in standardized test preparation, focusing on the GRE quantitative exam. Prior research has shown great potential for the utilization of…
Retrieval-Augmented Generation (RAG) enhances coding tasks by incorporating retrieved code examples into prompts. However, lengthy prompts, often exceeding tens of thousands of tokens, introduce challenges related to limited context windows…
Existing Computerized Adaptive Testing (CAT) frameworks typically select questions based on the predicted likelihood that the student will answer correctly. This design ignores information contained in students' open-ended responses,…
We study the problem of determining whether a piece of text has been authored by a human or by a large language model (LLM). Existing state of the art logits-based detectors make use of statistics derived from the log-probability of the…
Generative models lack rigorous statistical guarantees for their outputs and are therefore unreliable in safety-critical applications. In this work, we propose Sequential Conformal Prediction for Generative Models (SCOPE-Gen), a sequential…
Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples,…
The "Graph pre-training and fine-tuning" paradigm has significantly improved Graph Neural Networks(GNNs) by capturing general knowledge without manual annotations for downstream tasks. However, due to the immense gap of data and tasks…
Automatic evaluation metrics are indispensable for evaluating generated text. To date, these metrics have focused almost exclusively on the content selection aspect of the system output, ignoring the linguistic quality aspect altogether. We…
Gradual typing is an approach to integrating static and dynamic typing within the same language, and puts the programmer in control of which regions of code are type checked at compile-time and which are type checked at run-time. In this…
As popularity of algebraic effects and handlers increases, so does a demand for their efficient execution. Eff, an ML-like language with native support for handlers, has a subtyping-based effect system on which an effect-aware optimizing…
When mathematicians present proofs they usually adapt their explanations to their didactic goals and to the (assumed) knowledge of their addressees. Modern automated theorem provers, in contrast, present proofs usually at a fixed level of…
[Context] Modern AI applications increasingly process highly structured data, such as 3D meshes and point clouds, where test input generation must preserve both structural and semantic validity. However, existing fuzzing tools and input…
Recent advances in large language models have created new opportunities for stylometry, the study of writing styles and authorship. Two challenges, however, remain central: training generative models when no paired data exist, and…
Entity typing aims to assign types to the entity mentions in given texts. The traditional classification-based entity typing paradigm has two unignorable drawbacks: 1) it fails to assign an entity to the types beyond the predefined type…