Related papers: Coinductive Big-Step Semantics for Concurrency
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…
This position paper provides an interim summary on the goals and current state of our ongoing research project on semantic model differencing for software evolution. We describe the basics of semantic model differencing, give two examples…
Reversible distributed programs have the ability to abort unproductive computation paths and backtrack, while unwinding communication that occurred in the aborted paths. While it is natural to assume that reversibility implies full state…
Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning. We observe their interpretability and discuss their potential utility in a safety-critical context. Concretely, we propose to use them to add…
Large language models have exhibited intriguing in-context learning capability, achieving promising zero- and few-shot performance without updating the parameters. However, conventional in-context learning is usually restricted by length…
We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described…
Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive…
There are two main approaches to the distributed representation of words: low-dimensional deep learning embeddings and high-dimensional distributional models, in which each dimension corresponds to a context word. In this paper, we combine…
Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…
Labeling videos at scale is impractical. Consequently, self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image representations suggests contrastive learning is a promising…
Integration between biology and information science benefits both fields. Many related models have been proposed, such as computational visual cognition models, computational motor control models, integrations of both and so on. In general,…
We develop an approach for active semantic perception which refers to using the semantics of the scene for tasks such as exploration. We build a compact, hierarchical multi-layer scene graph that can represent large, complex indoor…
Large language models demonstrate limited capability in proficiency-controlled sentence simplification, particularly when simplifying across large readability levels. We propose a framework that decomposes complex simplifications into…
Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations. Existing methods have two main drawbacks. First, they overemphasize pairwise utterance…
Asynchronous computation and gradient compression have emerged as two key techniques for achieving scalability in distributed optimization for large-scale machine learning. This paper presents a unified analysis framework for distributed…
Large Language Models (LLMs) are intended to reflect human linguistic competencies. But humans have access to a broad and embodied context, which is key in detecting and resolving linguistic ambiguities, even in isolated text spans. A…
Prompt engineering has made significant contributions to the era of large language models, yet its effectiveness depends on the skills of a prompt author. This paper introduces $\textit{iPrOp}$, a novel interactive prompt optimization…
This paper makes two contributions to the field of text-based patent similarity. First, it compares the performance of different kinds of patent-specific pretrained embedding models, namely static word embeddings (such as word2vec and…
Step-by-step reasoning is widely used to enhance the reasoning ability of large language models (LLMs) in complex problems. Evaluating the quality of reasoning traces is crucial for understanding and improving LLM reasoning. However,…
Recent work has shown that convolutional neural networks (CNNs) can be applied successfully in disparity estimation, but these methods still suffer from errors in regions of low-texture, occlusions and reflections. Concurrently, deep…