Related papers: Faster Smarter Induction in Isabelle/HOL
We consider the problem of explaining the predictions of an arbitrary blackbox model $f$: given query access to $f$ and an instance $x$, output a small set of $x$'s features that in conjunction essentially determines $f(x)$. We design an…
Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to…
Standard automatic methods for recognizing problematic development commits can be greatly improved via the incremental application of human+artificial expertise. In this approach, called EMBLEM, an AI tool first explore the software…
Autocomplete suggestions are fundamental to modern text entry systems, with applications in domains such as messaging and email composition. Typically, autocomplete suggestions are generated from a language model with a confidence…
Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…
For a computational system to be intelligent, it should be able to perform, at least, basic deductions. Nonetheless, since deductions are, in some sense, equivalent to tautologies, it seems that they do not provide new information. The…
Despite recent advances in automating theorem proving in full first-order theories, inductive reasoning still poses a serious challenge to state-of-the-art theorem provers. The reason for that is that in first-order logic induction requires…
Efficiently querying data on embedded sensor and IoT devices is challenging given the very limited memory and CPU resources. With the increasing volumes of collected data, it is critical to process, filter, and manipulate data on the edge…
Semantic segmentation is a core task in computer vision. Existing methods are generally divided into two categories: automatic and interactive. Interactive approaches, exemplified by the Segment Anything Model (SAM), have shown promise as…
Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…
We present an executable formally verified SAT encoding of classical AI planning. We use the theorem prover Isabelle/HOL to perform the verification. We experimentally test the verified encoding and show that it can be used for reasonably…
The primary way of building AI applications is shifting from training specialist models to prompting generalist models. A common practice for prompting generalist models, often referred to as in-context learning, is to append a few examples…
Prompting methods recently achieve impressive success in few-shot learning. These methods modify input samples with prompt sentence pieces, and decode label tokens to map samples to corresponding labels. However, such a paradigm is very…
The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be…
In this paper, we tackle the problem of incrementally learning a classifier, one example at a time, directly on chip. To this end, we propose an efficient hardware implementation of a recently introduced incremental learning procedure that…
This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM). While LLMs have demonstrated remarkable ability in achieving high-quality annotation in various tasks, the…
We report our development of a simple but fast and efficient inductive unsupervised semantic tagger for Chinese words. A POS hand-tagged corpus of 348,000 words is used. The corpus is being tagged in two steps. First, possible semantic tags…
The goal of inductive logic programming is to search for a hypothesis that generalises training data and background knowledge. The challenge is searching vast hypothesis spaces, which is exacerbated because many logically equivalent…
Hybrid learning methods use theoretical knowledge of a domain and a set of classified examples to develop a method for classification. Methods that use domain knowledge have been shown to perform better than inductive learners. However,…
The task of inferring logical formulas from examples has garnered significant attention as a means to assist engineers in creating formal specifications used in the design, synthesis, and verification of computing systems. Among various…